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
    @Service
    -0.08
    ❄
    -0.07
    .vue
    -0.07
    кси
    -0.07
    torrent
    -0.06
    ollywood
    -0.06
     perspective
    -0.06
    "]').
    -0.06
    枫
    -0.06
    ｪ
    -0.06
    POSITIVE LOGITS
     crippled
    0.08
     strcmp
    0.08
    шая
    0.07
     simples
    0.07
     programm
    0.07
    пр
    0.07
     ign
    0.07
    Ef
    0.07
    INLINE
    0.07
     sacked
    0.07
    Act Density 0.090%

    No Known Activations