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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cars
    -0.07
     Repeat
    -0.07
    Evt
    -0.07
    웠
    -0.06
    _circle
    -0.06
    FindBy
    -0.06
     zeigen
    -0.06
     JB
    -0.06
     Ramos
    -0.06
     Bags
    -0.06
    POSITIVE LOGITS
    >");↵↵
    0.07
     barr
    0.07
     apl
    0.06
     aberr
    0.06
     سوم
    0.06
     singular
    0.06
    oubles
    0.06
    批
    0.06
     slaves
    0.06
    ！”
    0.06
    Act Density 0.002%

    No Known Activations