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

    Neuronpedia

    INDEX
    Explanations

    ible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ildren
    -0.07
    drink
    -0.07
    _even
    -0.07
    雨
    -0.06
     contentValues
    -0.06
    mensagem
    -0.06
    _lt
    -0.06
    ZY
    -0.06
     Nut
    -0.06
    ricula
    -0.06
    POSITIVE LOGITS
     jedin
    0.06
     jadx
    0.06
    Sibling
    0.06
     bidder
    0.05
    ”;
    0.05
     disposit
    0.05
    UED
    0.05
     esi
    0.05
     signature
    0.05
     pBuffer
    0.05
    Act Density 0.106%

    No Known Activations