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
     Macros
    -0.06
     Без
    -0.06
    �ng
    -0.06
     ให
    -0.06
     정신
    -0.05
     Wallpaper
    -0.05
    街
    -0.05
    rypted
    -0.05
     fitness
    -0.05
    ภาษ
    -0.05
    POSITIVE LOGITS
    NAMESPACE
    0.07
     setbacks
    0.07
     inté
    0.07
    tier
    0.06
     Inn
    0.06
     leve
    0.06
    놓
    0.06
    _rom
    0.06
     stack
    0.06
    菌
    0.06
    Act Density 0.001%

    No Known Activations