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

    Neuronpedia

    INDEX
    Explanations

    enough

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .UseText
    -0.07
    衝
    -0.06
     cancellationToken
    -0.06
    .qt
    -0.06
     玩
    -0.06
     Antar
    -0.06
    ontvangst
    -0.06
    Syntax
    -0.06
     материал
    -0.06
     acquisitions
    -0.05
    POSITIVE LOGITS
    Probability
    0.07
    minated
    0.07
     analyzer
    0.06
     legitimately
    0.06
     ｀
    0.06
     already
    0.06
    -Man
    0.06
    'id
    0.06
    redients
    0.06
    verb
    0.06
    Act Density 0.054%

    No Known Activations