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

    Neuronpedia

    INDEX
    Explanations

    character removal/manipulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    look
    -0.07
    ПО
    -0.06
     perfectly
    -0.06
    nier
    -0.06
    .instagram
    -0.06
    cw
    -0.06
     verir
    -0.06
    _Save
    -0.06
     recreated
    -0.06
     lessen
    -0.06
    POSITIVE LOGITS
     fiat
    0.08
     إي
    0.07
    tensorflow
    0.07
    ním
    0.06
    ाफ
    0.06
    HasColumnName
    0.06
    цією
    0.06
     پس
    0.06
    -fill
    0.06
    -radius
    0.06
    Act Density 0.003%

    No Known Activations