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

    Neuronpedia

    INDEX
    Explanations

    PM, self, text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     রোগ
    0.42
     Multivariate
    0.41
     Elvis
    0.41
     आइट
    0.40
     lice
    0.40
     Big
    0.40
    <0x1E>
    0.39
     খুঁজতে
    0.39
     বলতে
    0.38
     annoying
    0.38
    POSITIVE LOGITS
    text
    0.45
    文
    0.40
     vessel
    0.39
    suffixes
    0.39
    ടുത
    0.39
    form
    0.36
    schrift
    0.36
    щина
    0.36
    粘贴
    0.35
    豐
    0.35
    Act Density 0.000%

    No Known Activations