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

    Neuronpedia

    INDEX
    Explanations

    code and debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    פעילויות
    -0.07
    化妆品
    -0.07
    iconductor
    -0.07
     Circus
    -0.07
    运动会
    -0.07
     literacy
    -0.06
    ],[-
    -0.06
     админист
    -0.06
    cedures
    -0.06
     findOne
    -0.06
    POSITIVE LOGITS
    ﺘ
    0.08
     после
    0.07
    تباع
    0.07
    났
    0.07
     phúc
    0.07
     dwarf
    0.07
    -q
    0.07
     miraculous
    0.06
     groß
    0.06
    dre
    0.06
    Act Density 0.123%

    No Known Activations