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

    Neuronpedia

    INDEX
    Explanations

    new products, business, or dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ទៅ
    0.38
    ીએ
    0.38
     vrat
    0.37
    ři
    0.36
     exaggeration
    0.36
    iddy
    0.35
    udal
    0.34
    ulated
    0.34
     الترم
    0.34
    ๊ะ
    0.34
    POSITIVE LOGITS
     neuen
    1.00
     নতুন
    0.96
     новые
    0.96
     neue
    0.95
     nuevos
    0.95
     nuovi
    0.94
    新的
    0.94
     nieuwe
    0.93
     nuevas
    0.93
     nuove
    0.93
    Act Density 0.079%

    No Known Activations