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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (write
    -0.08
     whitelist
    -0.07
     Biggest
    -0.07
    .Special
    -0.07
    створ
    -0.07
     inject
    -0.07
     كرة
    -0.07
    -code
    -0.06
     투
    -0.06
    wart
    -0.06
    POSITIVE LOGITS
     GAS
    0.07
     amd
    0.06
     compromised
    0.06
     ميل
    0.06
    _MT
    0.06
    .species
    0.06
    于
    0.06
    IDAD
    0.05
     delays
    0.05
    ademic
    0.05
    Act Density 0.002%

    No Known Activations