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
    _svg
    -0.08
     ।↵↵
    -0.07
    ैक
    -0.07
     scream
    -0.07
    unch
    -0.06
    another
    -0.06
    Seconds
    -0.06
    _bool
    -0.06
    Truth
    -0.06
    oses
    -0.06
    POSITIVE LOGITS
     Ash
    0.07
     Pond
    0.06
     inconsistent
    0.06
     Drive
    0.06
    (course
    0.06
    .moveTo
    0.06
     Issue
    0.06
     %{
    0.06
     Απο
    0.06
    нач
    0.06
    Act Density 0.103%

    No Known Activations