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

    Neuronpedia

    INDEX
    Explanations

    junk characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lab
    -0.07
    두
    -0.06
    .Memory
    -0.06
     Ebony
    -0.06
    _MALLOC
    -0.06
     Müş
    -0.06
    есто
    -0.06
     leer
    -0.06
    -й
    -0.06
    VERBOSE
    -0.06
    POSITIVE LOGITS
    08
    0.07
    scripts
    0.06
    listing
    0.06
     sexy
    0.06
    game
    0.06
    arter
    0.06
     종
    0.06
     splash
    0.06
     ژاپ
    0.06
     indeed
    0.06
    Act Density 0.007%

    No Known Activations