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

    Neuronpedia

    INDEX
    Explanations

    seeking help or advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     און
    0.75
    ودی
    0.68
    प्ताहिक
    0.68
    承诺
    0.68
     intimated
    0.68
     госпо
    0.67
     Ausbildung
    0.67
    т
    0.67
     які
    0.65
    Own
    0.65
    POSITIVE LOGITS
     tento
    0.88
    seeker
    0.82
    ಸ್
    0.81
    rept
    0.79
    mamm
    0.79
    iscope
    0.77
    nickname
    0.77
    arquivo
    0.77
    rául
    0.76
    are
    0.75
    Act Density 0.000%

    No Known Activations