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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sample
    -0.07
    див
    -0.06
     utiliser
    -0.06
     faire
    -0.06
     bloque
    -0.06
     Architect
    -0.06
     Nine
    -0.06
     seven
    -0.06
     ava
    -0.06
    []}
    -0.06
    POSITIVE LOGITS
    �
    0.06
    _HALF
    0.06
    upon
    0.06
    �
    0.06
    アップ
    0.06
    hibited
    0.06
    977
    0.06
     Aub
    0.06
    CREASE
    0.06
    ض
    0.06
    Act Density 0.005%

    No Known Activations