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

    Neuronpedia

    INDEX
    Explanations

    programming variable types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Branch
    -0.07
    (amount
    -0.07
    ерин
    -0.07
     diş
    -0.07
     ambition
    -0.07
     organ
    -0.07
     Recipe
    -0.06
    ucer
    -0.06
     VALUES
    -0.06
     lâu
    -0.06
    POSITIVE LOGITS
    ,t
    0.06
     방송
    0.06
    forums
    0.06
     concurrent
    0.06
     experimented
    0.06
    _tools
    0.06
    ozo
    0.06
    инки
    0.06
    _EXPR
    0.06
     데
    0.05
    Act Density 0.003%

    No Known Activations