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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reated
    -0.06
    좀
    -0.06
    Great
    -0.06
     slide
    -0.06
    :init
    -0.06
    reat
    -0.06
    Moves
    -0.06
     LLC
    -0.06
    Это
    -0.06
    영
    -0.06
    POSITIVE LOGITS
     После
    0.07
     पड
    0.06
     kolem
    0.06
    sprintf
    0.06
     Dining
    0.06
    ffects
    0.06
     الصن
    0.06
     suất
    0.06
     propos
    0.06
     Ox
    0.06
    Act Density 0.018%

    No Known Activations