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

    Neuronpedia

    INDEX
    Explanations

    numbers, dollar signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilver
    -0.07
     мн
    -0.06
     Silver
    -0.06
     affiliates
    -0.06
    ejte
    -0.06
    ForeColor
    -0.06
    DISABLE
    -0.06
     UBND
    -0.06
    thed
    -0.06
     Genetics
    -0.06
    POSITIVE LOGITS
    ガ
    0.07
    ′
    0.07
    计算
    0.06
     муж
    0.06
    ─
    0.06
    ¸
    0.06
     Crit
    0.06
    ecektir
    0.06
    ♪
    0.06
     BRE
    0.06
    Act Density 0.035%

    No Known Activations