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

    Neuronpedia

    INDEX
    Explanations

    discussion points and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بك
    0.38
     Lokal
    0.38
     reich
    0.37
     bundling
    0.37
     ре
    0.37
     fresh
    0.37
     خپل
    0.36
     Cake
    0.36
     категория
    0.36
     subgroups
    0.35
    POSITIVE LOGITS
    gressive
    0.41
    gri
    0.41
    endent
    0.40
    Semaphore
    0.40
    aso
    0.40
    sem
    0.39
    dote
    0.39
    fc
    0.39
    jury
    0.39
    sexual
    0.39
    Act Density 0.000%

    No Known Activations