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

    Neuronpedia

    INDEX
    Explanations

    code/programming discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    今
    -0.07
    íny
    -0.07
     ди
    -0.07
     Block
    -0.06
     Vampire
    -0.06
     Blind
    -0.06
     Dream
    -0.06
     analytics
    -0.06
    _bool
    -0.06
    wear
    -0.06
    POSITIVE LOGITS
    Ma
    0.07
    huge
    0.06
    \core
    0.06
    *self
    0.06
     كسارة
    0.06
    ltra
    0.06
     kz
    0.06
     pretext
    0.06
    erdem
    0.06
    uden
    0.06
    Act Density 0.152%

    No Known Activations