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

    Neuronpedia

    INDEX
    Explanations

    code syntax and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    йдз
    0.40
    ತ್ರೆ
    0.40
    Ⴚ
    0.38
    Mel
    0.37
    dimensioni
    0.36
    ၞ
    0.36
    وجوان
    0.36
    ড়া
    0.35
     enkel
    0.35
    侗
    0.35
    POSITIVE LOGITS
    umis
    0.35
     Hold
    0.34
    good
    0.34
    args
    0.33
     Holds
    0.32
     assign
    0.32
    [:
    0.32
     ogr
    0.32
     связь
    0.32
     fatally
    0.31
    Act Density 0.007%

    No Known Activations