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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ンジ
    -0.07
    jezd
    -0.07
    ुर
    -0.06
     Wolfe
    -0.06
    documento
    -0.06
    tank
    -0.06
     때
    -0.06
    cairo
    -0.06
    ests
    -0.06
    ternal
    -0.06
    POSITIVE LOGITS
     Vince
    0.07
    erce
    0.07
     supplementary
    0.07
     Geld
    0.07
    ")↵↵
    0.06
    ";↵↵
    0.06
    ]);↵↵
    0.06
     Devin
    0.06
    เคล
    0.06
    ؟↵
    0.06
    Act Density 0.005%

    No Known Activations