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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -с
    -0.07
     originals
    -0.07
    ük
    -0.07
     negatives
    -0.06
     Zac
    -0.06
     отсутств
    -0.06
    _mass
    -0.06
    ](
    -0.06
     approve
    -0.06
    から
    -0.06
    POSITIVE LOGITS
     �
    0.07
     Ý
    0.06
     BM
    0.06
    _DIG
    0.06
    rimp
    0.06
    _BUILD
    0.06
    _FACTOR
    0.06
    .setSelection
    0.06
     disg
    0.06
     خیابان
    0.06
    Act Density 0.001%

    No Known Activations