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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र
    1.51
     erstwhile
    1.46
     인해
    1.31
    d
    1.25
    ే
    1.20
    ्स
    1.18
    Celebrating
    1.16
    ে
    1.16
    ी
    1.13
    Miscellaneous
    1.12
    POSITIVE LOGITS
     handel
    1.28
     duh
    1.16
    mus
    1.16
     vois
    1.15
     détail
    1.15
    $?
    1.12
     kezel
    1.12
     Kunst
    1.11
     זה
    1.10
     kok
    1.10
    Act Density 0.000%

    No Known Activations