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

    Neuronpedia

    INDEX
    Explanations

    article "a" or "an"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Day
    -0.07
     ژ
    -0.06
    734
    -0.06
     Transformers
    -0.06
     Az
    -0.06
     Reno
    -0.06
     substitution
    -0.06
     occurrences
    -0.06
     Drake
    -0.06
    Metric
    -0.06
    POSITIVE LOGITS
    (children
    0.06
    zzo
    0.06
    @student
    0.06
    ensitive
    0.06
     повыш
    0.06
     معت
    0.06
    bean
    0.06
    zení
    0.06
    ucceed
    0.06
    piry
    0.06
    Act Density 0.057%

    No Known Activations