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

    Neuronpedia

    INDEX
    Explanations

    candidate values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raided
    0.56
    testing
    0.53
    apati
    0.51
    ಾಗುತ್ತದೆ
    0.50
    wości
    0.50
     අය
    0.50
    جہ
    0.49
     tackled
    0.49
    toluene
    0.49
     کاهش
    0.49
    POSITIVE LOGITS
    q
    0.46
    CFLAGS
    0.46
    ás
    0.44
     clearContext
    0.44
    is
    0.44
    os
    0.44
     AUTOM
    0.42
     transforma
    0.42
     ultram
    0.42
    as
    0.42
    Act Density 0.000%

    No Known Activations