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

    Neuronpedia

    INDEX
    Explanations

    Em

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aan
    -0.07
     *
↵
    -0.07
    Returns
    -0.07
     indications
    -0.06
    死
    -0.06
    沒有
    -0.06
     Treaty
    -0.06
     [
    -0.06
     Jahren
    -0.06
    _integer
    -0.06
    POSITIVE LOGITS
     brunette
    0.06
     znaj
    0.06
    ,axis
    0.06
     podrob
    0.06
    وروب
    0.06
    ЛО
    0.06
    _COMPANY
    0.06
     midi
    0.06
     PTR
    0.06
    Tech
    0.06
    Act Density 0.006%

    No Known Activations