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

    Neuronpedia

    INDEX
    Explanations

    Stop words/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .back
    -0.07
     ух
    -0.07
     Reject
    -0.07
    ID
    -0.06
    ;width
    -0.06
    oken
    -0.06
     firmly
    -0.06
     gute
    -0.06
     тка
    -0.06
    -cover
    -0.06
    POSITIVE LOGITS
     Reconstruction
    0.07
    ีย
    0.06
     Lớp
    0.06
     ASS
    0.06
    chedules
    0.06
    Prov
    0.06
     Slovakia
    0.06
    زر
    0.06
     LinearGradient
    0.06
     pig
    0.06
    Act Density 0.000%

    No Known Activations