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

    Neuronpedia

    INDEX
    Explanations

    code and language examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    configs
    -0.06
    ्तर
    -0.06
    ськими
    -0.06
     مردم
    -0.05
    _info
    -0.05
    _pf
    -0.05
    MethodName
    -0.05
     Appe
    -0.05
    ‌شوند
    -0.05
    )은
    -0.05
    POSITIVE LOGITS
     Gree
    0.07
    aying
    0.07
     Tatto
    0.07
    
    0.06
     Bordeaux
    0.06
     guidance
    0.06
     Plzeň
    0.06
    .cid
    0.06
    Domin
    0.06
    .nc
    0.06
    Act Density 0.024%

    No Known Activations