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

    Neuronpedia

    INDEX
    Explanations

    modeldeploying models or systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    preet
    1.66
    )};
    1.60
    ya
    1.59
    ্স
    1.57
     limbo
    1.56
    )}^{\
    1.55
    ່າງ
    1.51
    ければ
    1.50
     absoluto
    1.50
    dbjc
    1.50
    POSITIVE LOGITS
    د
    2.58
    ে
    2.34
    ه
    2.33
    ни
    2.28
    ל
    2.19
    א
    2.17
    i
    2.16
    ص
    2.13
    ال
    2.08
    the
    2.05
    Act Density 0.013%

    No Known Activations