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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron remains inactive (all activations are zero) and thus does not detect any specific pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     barren
    -0.06
     grapes
    -0.06
    quets
    -0.06
    鼓
    -0.06
     whim
    -0.06
     Kill
    -0.06
    DBG
    -0.06
     Desired
    -0.06
     Qing
    -0.06
     Build
    -0.06
    POSITIVE LOGITS
    ."\
    0.07
    _removed
    0.07
     detal
    0.07
    .plist
    0.07
     ủy
    0.06
    ()?
    0.06
    _disconnect
    0.06
     Premium
    0.06
    .Infrastructure
    0.06
    (error
    0.06
    Act Density 0.005%

    No Known Activations