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

    Neuronpedia

    INDEX
    Explanations

    UNESCO

    np_max-act · gemini-2.0-flash

    requests for travel planning and itineraries.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron is effectively “dead” – it never responds (all activations are zero) and thus detects no patterns in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     '**
    -0.07
     ArrayAdapter
    -0.06
     HttpStatus
    -0.06
     heating
    -0.06
    _IOCTL
    -0.06
    '%
    -0.06
    _own
    -0.06
     Bra
    -0.06
    "But
    -0.06
    _ValueChanged
    -0.06
    POSITIVE LOGITS
     UNESCO
    0.12
    esco
    0.10
    ESCO
    0.08
    ん
    0.07
     lugares
    0.07
     ещё
    0.07
     freelance
    0.07
    awesome
    0.07
     الجم
    0.07
     wykon
    0.07
    Act Density 0.000%

    No Known Activations