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

    Neuronpedia

    INDEX
    Explanations

    and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ওয়া
    0.73
     EPO
    0.71
    ప్ర
    0.69
    MOT
    0.69
    ILE
    0.68
    ഗോ
    0.68
    バン
    0.67
    EST
    0.66
    协商
    0.66
    ETO
    0.66
    POSITIVE LOGITS
    fläche
    0.99
    flächen
    0.85
     bestehen
    0.84
     stärker
    0.82
     вокруг
    0.81
    вый
    0.80
    ющее
    0.80
    де
    0.80
     Fläche
    0.80
     begeistert
    0.80
    Act Density 0.004%

    No Known Activations