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

    Neuronpedia

    INDEX
    Explanations

    .m or .a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uco
    -0.07
    意思是
    -0.07
    roring
    -0.07
     aph
    -0.06
    RowIndex
    -0.06
     caric
    -0.06
    roscope
    -0.06
    getti
    -0.06
     for
    -0.06
     Trotsky
    -0.06
    POSITIVE LOGITS
    _EXTENSIONS
    0.07
     CLEAR
    0.07
    AGE
    0.07
     POWER
    0.07
     Steam
    0.07
    _GF
    0.07
     חינם
    0.07
    ード
    0.07
     ceased
    0.06
    .getUser
    0.06
    Act Density 0.002%

    No Known Activations