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

    Neuronpedia

    INDEX
    Explanations

    hyphens

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rep
    0.85
    சென்னை
    0.80
    YM
    0.79
    abbr
    0.74
    itude
    0.73
    РС
    0.73
    UALA
    0.73
    APB
    0.73
    unta
    0.73
     Rep
    0.73
    POSITIVE LOGITS
     hood
    0.92
     hoàng
    0.88
     glow
    0.88
     parks
    0.86
     kill
    0.83
     glows
    0.81
     profits
    0.80
     struggles
    0.77
     domains
    0.77
     graces
    0.76
    Act Density 0.000%

    No Known Activations