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

    Neuronpedia

    INDEX
    Explanations

    83

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    庆
    -0.07
     clit
    -0.07
    vfs
    -0.07
    .Replace
    -0.06
    lenmesi
    -0.06
     podmínek
    -0.06
     ссыл
    -0.06
    �
    -0.06
     safer
    -0.06
     +↵
    -0.06
    POSITIVE LOGITS
    ují
    0.07
     또한
    0.06
     folding
    0.06
    атків
    0.06
    German
    0.06
     western
    0.06
     pageNumber
    0.06
    (kind
    0.06
     Folding
    0.06
    0.06
    Act Density 0.004%

    No Known Activations