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

    Neuronpedia

    INDEX
    Explanations

    found to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     not
    -2.00
    operazione
    -1.63
     办
    -1.57
    RetentionPolicy
    -1.54
     a
    -1.52
     Different
    -1.51
    atother
    -1.51
     During
    -1.50
     Then
    -1.48
    ”（
    -1.48
    POSITIVE LOGITS
     deras
    1.66
     vão
    1.63
     gewiß
    1.59
     kolon
    1.55
     ralla
    1.54
     amenaz
    1.52
     новым
    1.50
     detta
    1.49
     detenidos
    1.48
    夬
    1.47
    Act Density 0.027%

    No Known Activations