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

    Neuronpedia

    INDEX
    Explanations

    ---

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /workspace
    -0.08
    بول
    -0.07
    //
    -0.07
    algorithm
    -0.06
    .addTo
    -0.06
     yapıldı
    -0.06
     FOLLOW
    -0.06
     �
    -0.06
    }//
    -0.06
    _BLK
    -0.06
    POSITIVE LOGITS
     prejudices
    0.06
    title
    0.06
    (tmp
    0.06
     Trick
    0.06
     yummy
    0.06
     이야
    0.06
    .','
    0.06
    _dw
    0.06
    εβ
    0.06
    査
    0.06
    Act Density 0.004%

    No Known Activations