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

    Neuronpedia

    INDEX
    Explanations

    backtick

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pond
    0.76
     Dien
    0.74
     svět
    0.73
    জিস্ট
    0.72
    낯
    0.72
     Pred
    0.71
     strom
    0.71
     Fond
    0.70
     Screen
    0.69
    cf
    0.69
    POSITIVE LOGITS
    ticks
    1.02
     sl
    0.85
    sl
    0.80
     ticks
    0.74
    स्
    0.71
    হত্যা
    0.70
    muş
    0.69
    َ
    0.69
    uffles
    0.68
    tick
    0.68
    Act Density 0.006%

    No Known Activations