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

    Neuronpedia

    INDEX
    Explanations

    email

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surfaced
    -0.06
     Voy
    -0.06
    FY
    -0.06
    Codigo
    -0.06
     Appeals
    -0.06
    iert
    -0.06
     Đồng
    -0.06
    Boot
    -0.06
     videoer
    -0.06
    	dialog
    -0.06
    POSITIVE LOGITS
    促
    0.07
    hib
    0.06
     Dagger
    0.06
    质量
    0.06
    arbon
    0.06
     oli
    0.06
    _method
    0.06
    .ht
    0.06
    [s
    0.06
    JKLM
    0.06
    Act Density 0.012%

    No Known Activations