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

    Neuronpedia

    INDEX
    Explanations

    code related symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     penalty
    -0.06
     helpers
    -0.06
     увагу
    -0.06
    .spaceBetween
    -0.06
    شف
    -0.06
     ///↵
    -0.06
    TP
    -0.06
     مثلا
    -0.06
    /feed
    -0.06
     삼성
    -0.06
    POSITIVE LOGITS
    _slots
    0.07
     ngOnInit
    0.07
    ritic
    0.07
     Sistem
    0.07
    .final
    0.07
     Nina
    0.06
     Haven
    0.06
    Euro
    0.06
     quel
    0.06
     Châu
    0.06
    Act Density 0.154%

    No Known Activations