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

    Neuronpedia

    INDEX
    Explanations

    Color, magnitude, and digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     médico
    -0.08
    ****↵
    -0.07
     suspected
    -0.07
     shouted
    -0.07
     TA
    -0.06
    "})↵
    -0.06
    决赛
    -0.06
    }))↵
    -0.06
     Bra
    -0.06
    )")↵
    -0.06
    POSITIVE LOGITS
    modulo
    0.07
    _bb
    0.07
     trendy
    0.07
    經濟
    0.07
    嘚
    0.07
     Hob
    0.06
     obey
    0.06
     empez
    0.06
     Box
    0.06
    毽
    0.06
    Act Density 0.060%

    No Known Activations