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

    Neuronpedia

    INDEX
    Explanations

    matching passwords or values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bán
    -0.06
    _physical
    -0.06
    igma
    -0.06
     Gaul
    -0.06
    是在
    -0.06
     �
    -0.06
     importante
    -0.06
    átek
    -0.06
     falta
    -0.06
    άβ
    -0.06
    POSITIVE LOGITS
     Bí
    0.07
     เขต
    0.07
    ЮЛ
    0.07
     io
    0.06
    Intern
    0.06
     Kle
    0.06
    ([
↵
    0.06
     Sega
    0.06
    dpi
    0.06
     urč
    0.06
    Act Density 0.174%

    No Known Activations