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

    Neuronpedia

    INDEX
    Explanations

    code structures and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geme
    0.39
     Vard
    0.39
     Answer
    0.39
     foot
    0.37
     Ange
    0.36
     KN
    0.36
     answered
    0.36
     argent
    0.36
     Chapman
    0.36
     autom
    0.35
    POSITIVE LOGITS
    উজ
    0.44
    梦
    0.43
    жения
    0.41
    akanan
    0.41
    граммы
    0.40
    грама
    0.39
     folhas
    0.39
    癌症
    0.39
    WMN
    0.38
    Fifty
    0.38
    Act Density 0.001%

    No Known Activations