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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     convent
    -0.07
    區
    -0.07
    ši
    -0.07
     ";↵
    -0.07
     císa
    -0.07
     मश
    -0.06
    _details
    -0.06
    .Toggle
    -0.06
     Král
    -0.06
    !");
↵
    -0.06
    POSITIVE LOGITS
     basic
    0.07
     destination
    0.07
     Cheng
    0.06
     timber
    0.06
    128
    0.06
    بن
    0.06
    千
    0.06
    ิจกรรม
    0.06
     random
    0.06
    ipher
    0.06
    Act Density 0.015%

    No Known Activations