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

    Neuronpedia

    INDEX
    Explanations

    stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    angen
    -0.07
     العم
    -0.06
    init
    -0.06
     =================================================
    -0.06
     그를
    -0.06
     Comprehensive
    -0.06
     Cemetery
    -0.06
    lections
    -0.06
     knocking
    -0.06
     Fakült
    -0.06
    POSITIVE LOGITS
     HMAC
    0.07
    .IntegerField
    0.06
    .utilities
    0.06
     Muscle
    0.06
    νε
    0.06
    扎
    0.06
    .blog
    0.06
     tasty
    0.06
    辦
    0.06
    uper
    0.06
    Act Density 0.002%

    No Known Activations