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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     여성
    -0.08
     csrf
    -0.07
     گوشی
    -0.07
     Tool
    -0.07
     TestCase
    -0.07
     Spider
    -0.07
     ACCESS
    -0.07
     summers
    -0.07
    prit
    -0.07
     Ass
    -0.07
    POSITIVE LOGITS
    .Autowired
    0.06
    _ver
    0.06
     بهتر
    0.06
    บอก
    0.05
     ICT
    0.05
    seudo
    0.05
    REFERENCES
    0.05
    шев
    0.05
     zal
    0.05
    HOST
    0.05
    Act Density 0.030%

    No Known Activations