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

    Neuronpedia

    INDEX
    Explanations

    -ism ideologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ς
    1.77
    ൽ
    1.70
     angegeben
    1.63
    ق
    1.60
    ן
    1.55
    Das
    1.53
    থাৎ
    1.51
    p
    1.51
     erforderlich
    1.48
    О
    1.48
    POSITIVE LOGITS
    лизм
    1.54
    主义
    1.52
    OS
    1.48
    nels
    1.45
    nz
    1.37
    n
    1.36
    ikaze
    1.34
    ంక
    1.33
    नपुर
    1.30
    нский
    1.30
    Act Density 0.070%

    No Known Activations