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

    Neuronpedia

    INDEX
    Explanations

    Suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restrain
    -0.07
     reaff
    -0.06
     bene
    -0.06
     generation
    -0.06
     magazines
    -0.06
    ーニ
    -0.06
     Shepherd
    -0.06
    $m
    -0.06
     emot
    -0.06
     humane
    -0.06
    POSITIVE LOGITS
    ẳ
    0.07
    nut
    0.06
     �
    0.06
    registration
    0.06
    .userData
    0.06
    iou
    0.06
    rary
    0.06
    dığ
    0.06
    Margin
    0.06
     Ptr
    0.06
    Act Density 0.119%

    No Known Activations