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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _response
    -0.07
     commenter
    -0.06
    352
    -0.06
    Instruction
    -0.06
    _expression
    -0.06
     supplementary
    -0.06
    uja
    -0.06
    _radius
    -0.06
    four
    -0.06
     swapped
    -0.06
    POSITIVE LOGITS
    ливість
    0.07
    ецт
    0.07
    lsru
    0.07
    キング
    0.06
    deş
    0.06
    ッグ
    0.06
     Мон
    0.06
    CHILD
    0.06
    issional
    0.06
    _TRI
    0.06
    Act Density 0.002%

    No Known Activations