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

    Neuronpedia

    INDEX
    Explanations

    handle game rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    έλ
    0.52
     حي
    0.49
     uncertainties
    0.46
    𝙢
    0.46
    ܣ
    0.45
    0.45
     دھو
    0.45
    жда
    0.45
     siècles
    0.45
    tar
    0.44
    POSITIVE LOGITS
    (
    0.48
    Biology
    0.46
    ARA
    0.46
    ادی
    0.46
    ID
    0.43
     Spectroscopy
    0.43
    IT
    0.43
     Biochemistry
    0.42
     Booster
    0.42
    ous
    0.42
    Act Density 0.001%

    No Known Activations