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

    Neuronpedia

    INDEX
    Explanations

    coral

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "time
    -0.07
     Leaf
    -0.07
    יפוי
    -0.07
    麋
    -0.07
    _CMP
    -0.06
     lợi
    -0.06
     취
    -0.06
    豨
    -0.06
    'L
    -0.06
     grief
    -0.06
    POSITIVE LOGITS
    เทคโน
    0.07
     ça
    0.07
    不经意
    0.07
    悄然
    0.07
    뻗
    0.07
    binding
    0.07
    getContext
    0.07
    Genres
    0.07
    weakSelf
    0.07
     funciona
    0.07
    Act Density 0.044%

    No Known Activations