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

    Neuronpedia

    INDEX
    Explanations

    XML namespaces, scripts, fiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    H
    0.53
    V
    0.53
    𝐸
    0.51
    城
    0.50
    城的
    0.49
     ETFs
    0.48
    Š
    0.47
     Rout
    0.47
     Kanton
    0.46
    Tou
    0.46
    POSITIVE LOGITS
    onya
    0.46
    መት
    0.45
     trav
    0.44
    ሯ
    0.43
    тельного
    0.43
     വിവിധ
    0.43
    լ
    0.43
    whal
    0.42
    тел
    0.42
    тельных
    0.42
    Act Density 0.001%

    No Known Activations