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

    Neuronpedia

    INDEX
    Explanations

    un, power

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _management
    -0.08
    कर
    -0.07
     하는
    -0.06
    Often
    -0.06
    ้าว
    -0.06
    [table
    -0.06
    _owner
    -0.06
     hour
    -0.06
     clarified
    -0.06
    .if
    -0.06
    POSITIVE LOGITS
     commentaire
    0.06
     року
    0.06
     česk
    0.06
    екси
    0.06
     competed
    0.06
    (boost
    0.06
    ège
    0.06
     sport
    0.06
     сторон
    0.06
     найб
    0.06
    Act Density 0.058%

    No Known Activations