Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    tip/advice

    np_max-act · gemini-2.0-flash

    The neuron fires on “tip” call-outs (e.g. “Pro tip:”, “Insider tip:”, “Insider secret:”, etc.) that introduce advice or handy hints.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information related to the performance and execution of business strategies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ides
    -0.07
    .opendaylight
    -0.06
     bases
    -0.06
     ground
    -0.06
    olute
    -0.06
     目
    -0.06
     Hydro
    -0.06
    815
    -0.06
    ्बर
    -0.06
     бенз
    -0.06
    POSITIVE LOGITS
    $model
    0.07
    Turkey
    0.07
     disruption
    0.07
     TCHAR
    0.07
    Truth
    0.07
    (!_
    0.07
     {}).
    0.07
    ête
    0.07
    Union
    0.07
    _Id
    0.06
    Act Density 0.010%

    No Known Activations