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

    Neuronpedia

    INDEX
    Explanations

    except

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    煳
    -0.08
    ush
    -0.07
     screaming
    -0.07
    usions
    -0.07
    adem
    -0.06
    _HE
    -0.06
     flash
    -0.06
    ！↵↵
    -0.06
     feels
    -0.06
    @
    -0.06
    POSITIVE LOGITS
    ainter
    0.07
     appropriations
    0.07
     midpoint
    0.07
    WSTR
    0.07
    zeros
    0.07
     Jobs
    0.06
    Endpoint
    0.06
     мобиль
    0.06
    pixel
    0.06
    histor
    0.06
    Act Density 0.002%

    No Known Activations