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

    Neuronpedia

    INDEX
    Explanations

    whether there, tell me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     French
    0.54
    PCA
    0.50
    8
    0.50
     \
    0.50
    ICC
    0.50
    BD
    0.49
    ناوی
    0.49
    With
    0.48
     δο
    0.48
    USING
    0.48
    POSITIVE LOGITS
     картина
    0.65
     rjf
    0.63
     heft
    0.62
    栯
    0.58
    ございました
    0.58
    worthiness
    0.57
     shortcoming
    0.57
    appré
    0.56
     يجعل
    0.55
    iophorus
    0.54
    Act Density 2.220%

    No Known Activations