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

    Neuronpedia

    INDEX
    Explanations

    citation and reference commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msch
    0.73
    Cl
    0.72
    Letter
    0.68
     jaaye
    0.63
    XMLHttpRequest
    0.63
     Letter
    0.62
     ۾
    0.62
    Eloquent
    0.62
    ূর্ন
    0.62
    áról
    0.61
    POSITIVE LOGITS
     pink
    0.80
    pink
    0.72
    ndham
    0.70
    ピンク
    0.69
    льных
    0.67
    akeda
    0.66
     Dole
    0.65
     Til
    0.65
     ajuste
    0.63
     tats
    0.63
    Act Density 0.002%

    No Known Activations