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

    Neuronpedia

    INDEX
    Explanations

    foreign language phrases

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     benzoate
    0.47
     let
    0.43
     os
    0.42
     запо
    0.41
     allo
    0.41
     zal
    0.40
     Temps
    0.40
     VO
    0.40
     lamb
    0.39
     sel
    0.38
    POSITIVE LOGITS
    暨
    0.41
    مرة
    0.41
    jing
    0.39
     исследователь
    0.39
     پیم
    0.37
    once
    0.37
     Merrick
    0.37
     एकदा
    0.36
    ॔
    0.36
     headway
    0.36
    Act Density 0.001%

    No Known Activations