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

    Neuronpedia

    INDEX
    Explanations

    computer code, math, languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egative
    -0.07
    ANDARD
    -0.07
    anmar
    -0.07
     todav
    -0.07
    感动
    -0.07
     enormous
    -0.06
     Außen
    -0.06
    的趋势
    -0.06
    莛
    -0.06
    知名的
    -0.06
    POSITIVE LOGITS
     bied
    0.07
    ⏳
    0.06
    Pale
    0.06
    ���
    0.06
     rejects
    0.06
    Ｅ
    0.06
    મ
    0.06
    ಯ
    0.06
    잉
    0.06
    PHY
    0.06
    Act Density 0.000%

    No Known Activations