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

    Neuronpedia

    INDEX
    Explanations

    Random text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.79
    Климат
    -0.78
    ]})
    -0.68
    ⓘ
    -0.66
    COUVER
    -0.65
    enumi
    -0.65
    yarnpkg
    -0.65
    }))
    -0.64
    saraba
    -0.63
    UPAC
    -0.62
    POSITIVE LOGITS
    ating
    0.47
    toContain
    0.46
    ings
    0.46
    WTS
    0.45
     Taktlose
    0.45
     bills
    0.45
    üstü
    0.45
    SPATH
    0.44
    Демо
    0.44
     <=",
    0.44
    Act Density 0.053%

    No Known Activations