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

    Neuronpedia

    INDEX
    Explanations

    difference

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alma
    -0.07
    omatic
    -0.07
     paraph
    -0.07
    Na
    -0.07
    各级
    -0.07
    更
    -0.07
    璃
    -0.07
     vistas
    -0.06
    驾
    -0.06
     orders
    -0.06
    POSITIVE LOGITS
    _DECREF
    0.07
    好久
    0.07
    %">
    0.07
    (parts
    0.07
    -chat
    0.07
    работать
    0.06
    tp
    0.06
     rice
    0.06
    IntegerField
    0.06
     ويم
    0.06
    Act Density 0.020%

    No Known Activations