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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Linden
    -0.07
     desktop
    -0.07
     stil
    -0.06
     رسول
    -0.06
     zajím
    -0.06
     trì
    -0.06
     hoạch
    -0.06
     cần
    -0.06
    ุทธ
    -0.06
    에서
    -0.06
    POSITIVE LOGITS
    SOURCE
    0.07
    WHERE
    0.07
    Und
    0.06
    gow
    0.06
     slope
    0.06
    -backed
    0.06
    EFF
    0.06
     pří
    0.06
    icom
    0.06
    rawtypes
    0.06
    Act Density 0.012%

    No Known Activations