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

    Neuronpedia

    INDEX
    Explanations

    Appearance/Description

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of a character’s physical appearance (the word “appearance” and related context).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Update
    -0.07
    _read
    -0.07
     жизнь
    -0.06
     petals
    -0.06
    情報
    -0.06
    智能
    -0.06
     Madagascar
    -0.06
    ủy
    -0.06
    olidays
    -0.06
    tem
    -0.06
    POSITIVE LOGITS
    .getChild
    0.07
    )$_
    0.07
    .ToDouble
    0.06
     RVA
    0.06
    @media
    0.06
     targeting
    0.06
     Cf
    0.06
     famil
    0.06
     Dynam
    0.06
     thanh
    0.06
    Act Density 0.046%

    No Known Activations