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

    Neuronpedia

    INDEX
    Explanations

    10 and 100

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    D
    0.45
     ways
    0.43
     ಪರ
    0.38
     Freedom
    0.38
     Herb
    0.38
    E
    0.38
     Harb
    0.37
    ONT
    0.37
     Ways
    0.37
    Ih
    0.36
    POSITIVE LOGITS
    barrels
    0.41
    वाड़ा
    0.40
    facts
    0.40
    baarheid
    0.39
    壹百
    0.39
     inputBox
    0.39
    十年
    0.38
    嬅
    0.38
    лән
    0.38
    showinfo
    0.38
    Act Density 0.011%

    No Known Activations