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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deserve
    -0.06
     Berm
    -0.06
     Nun
    -0.06
     dread
    -0.06
    clar
    -0.06
    -compatible
    -0.06
     Patt
    -0.06
    �
    -0.06
     comparer
    -0.06
     Mess
    -0.06
    POSITIVE LOGITS
    :'/
    0.07
     tight
    0.06
    ão
    0.06
     imprimir
    0.06
    場合は
    0.06
    选
    0.06
    .OrderBy
    0.06
     promotion
    0.06
    arry
    0.06
    leanor
    0.06
    Act Density 0.045%

    No Known Activations