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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ryn
    -0.07
     maman
    -0.07
     therapeutic
    -0.07
     Coaching
    -0.06
     Polar
    -0.06
    体贴
    -0.06
     lonely
    -0.06
     tua
    -0.06
    ir
    -0.06
    _logo
    -0.06
    POSITIVE LOGITS
     ballpark
    0.07
    Cheers
    0.07
    завис
    0.07
    碹
    0.07
     הזכ
    0.07
    裎
    0.07
    ずに
    0.06
    iParam
    0.06
     schw
    0.06
    -guard
    0.06
    Act Density 0.196%

    No Known Activations