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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     immobil
    -0.07
    }{
    -0.06
     prefect
    -0.06
     Different
    -0.06
     Kot
    -0.06
     isValid
    -0.06
     caller
    -0.06
    modes
    -0.06
    grey
    -0.06
    .plugin
    -0.06
    POSITIVE LOGITS
    ومتر
    0.07
     серд
    0.07
     lẫn
    0.06
     Méd
    0.06
    rink
    0.06
    .ReadToEnd
    0.06
    اون
    0.06
    พระ
    0.06
    -alpha
    0.06
    ินการ
    0.06
    Act Density 0.019%

    No Known Activations