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
     фак
    -0.06
     спост
    -0.06
     Mas
    -0.06
     Ή
    -0.06
     NF
    -0.06
     paylaş
    -0.06
    CharArray
    -0.06
     potassium
    -0.06
     Mod
    -0.06
    شان
    -0.06
    POSITIVE LOGITS
    salary
    0.06
    isateur
    0.06
    造
    0.06
     lokale
    0.06
     землю
    0.06
    -money
    0.06
     Recently
    0.06
    .isSuccess
    0.06
    /',
    0.06
    RIA
    0.06
    Act Density 0.000%

    No Known Activations