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
    eated
    -0.07
     已
    -0.07
     뿐
    -0.07
    .Range
    -0.06
     Voor
    -0.06
     Trigger
    -0.06
     backwards
    -0.06
     generar
    -0.06
    مت
    -0.06
     obstacles
    -0.06
    POSITIVE LOGITS
    asy
    0.07
    limits
    0.07
    imits
    0.07
    ）。↵
    0.07
    crease
    0.07
    elic
    0.06
    oundation
    0.06
    abase
    0.06
    .";
↵
    0.06
    ottle
    0.06
    Act Density 0.027%

    No Known Activations