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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incarceration
    -0.08
    Length
    -0.08
    óst
    -0.07
    .int
    -0.07
     vind
    -0.07
     corrobor
    -0.07
    镘
    -0.06
    combined
    -0.06
    .ForegroundColor
    -0.06
    ประธาน
    -0.06
    POSITIVE LOGITS
    ％
    0.07
     proprietà
    0.07
     película
    0.07
     הבי
    0.07
    Teams
    0.07
    (cmp
    0.07
    :');↵
    0.07
    英镑
    0.07
     hx
    0.07
     système
    0.07
    Act Density 0.003%

    No Known Activations