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

    Neuronpedia

    INDEX
    Explanations

    Technical or code related snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тот
    -0.08
     finer
    -0.08
     затем
    -0.08
    두
    -0.07
    留
    -0.07
    .green
    -0.07
    �
    -0.07
    .this
    -0.07
     explosive
    -0.07
    منت
    -0.07
    POSITIVE LOGITS
    :↵↵↵
    0.08
    專家
    0.07
    ();
↵
↵
    0.07
    -origin
    0.07
     case
    0.07
     "`
    0.07
    風險
    0.07
    )
↵
↵
↵
    0.07
    Ǧ
    0.07
    諮詢
    0.07
    Act Density 0.000%

    No Known Activations