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

    Neuronpedia

    INDEX
    Explanations

    knowledge, often, grammar, use, emotionally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রেসক্লা
    0.52
    തായ
    0.50
    ℧
    0.46
    aia
    0.45
     whims
    0.45
    uitar
    0.43
    ग्विजय
    0.43
     Mugh
    0.43
     প্রতিক
    0.42
    lias
    0.42
    POSITIVE LOGITS
    卫
    0.44
    arie
    0.44
    어
    0.43
     Australien
    0.42
    📈
    0.42
    ك
    0.41
     Netz
    0.41
    <0x94>
    0.41
    ح
    0.40
     Australian
    0.39
    Act Density 0.001%

    No Known Activations