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

    Neuronpedia

    INDEX
    Explanations

    one side / sided

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    р
    0.93
    ো
    0.92
    n
    0.88
    ів
    0.88
     listrik
    0.82
    ⢿
    0.82
    ுகிறார்கள்
    0.79
    ד
    0.78
    xing
    0.77
    ਮ
    0.77
    POSITIVE LOGITS
     Америки
    0.65
    handed
    0.64
     Hing
    0.64
    erb
    0.63
    गतान
    0.62
    ton
    0.61
     llegar
    0.61
    ighi
    0.61
     influent
    0.61
    اتی
    0.61
    Act Density 0.077%

    No Known Activations