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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ï
    -0.07
    Blocked
    -0.07
    Buy
    -0.07
    Color
    -0.07
    embu
    -0.07
     Dual
    -0.07
    Fetch
    -0.07
     przeci
    -0.07
    .fetch
    -0.07
    fus
    -0.06
    POSITIVE LOGITS
     व्यवहार
    0.09
     spät
    0.09
     Trent
    0.08
     exced
    0.08
     exceed
    0.08
     ges
    0.08
     habitudes
    0.07
    erweise
    0.07
     đẹp
    0.07
    پاکستان
    0.07
    Act Density 0.067%

    No Known Activations