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

    Neuronpedia

    INDEX
    Explanations

    effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Symphony
    -0.07
    @s
    -0.07
    .phase
    -0.06
     кон
    -0.06
    -shopping
    -0.06
    _Insert
    -0.06
     debated
    -0.06
     Duke
    -0.06
    gp
    -0.06
     questionable
    -0.06
    POSITIVE LOGITS
     державного
    0.07
    ZeroWidthSpace
    0.06
     tỉnh
    0.06
    gravity
    0.06
    krit
    0.06
    EventData
    0.06
     wykon
    0.06
    krom
    0.06
    salt
    0.06
    _SOFT
    0.06
    Act Density 0.049%

    No Known Activations