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

    Neuronpedia

    INDEX
    Explanations

    words beginning with B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nością
    0.37
    ivă
    0.36
    ্যন্তরীণ
    0.35
    ności
    0.34
     등으로
    0.34
    📰
    0.34
     तैनाती
    0.33
    ವ್
    0.33
    ຯ
    0.33
     강력
    0.32
    POSITIVE LOGITS
     B
    0.86
     b
    0.79
    B
    0.68
    autiful
    0.57
     Better
    0.54
    b
    0.54
    haviour
    0.51
     bland
    0.51
     ب
    0.51
     ב
    0.51
    Act Density 0.079%

    No Known Activations