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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蒺
    -0.07
     disin
    -0.07
    total
    -0.07
    valuation
    -0.07
     Performs
    -0.07
     التع
    -0.07
    排放
    -0.07
    称之为
    -0.07
     nhiễm
    -0.07
     df
    -0.07
    POSITIVE LOGITS
     EDGE
    0.07
    szedł
    0.07
    _fk
    0.07
    >",↵
    0.06
    >>();↵↵
    0.06
    ?;↵↵
    0.06
    (',');↵
    0.06
    뾔
    0.06
    covers
    0.06
     lounge
    0.06
    Act Density 0.118%

    No Known Activations