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

    Neuronpedia

    INDEX
    Explanations

    business profitability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \"
    -2.89
    1
    -2.61
     ``
    -2.50
     intenta
    -2.23
    ホント
    -2.23
     «
    -2.20
    满脸
    -2.08
    主に
    -2.06
    ができ
    -2.06
     aporta
    -2.05
    POSITIVE LOGITS
    ”？
    3.11
    𓆜
    2.77
    挹
    2.61
     принад
    2.52
    quele
    2.39
    ：（
    2.38
    轶
    2.30
     Mulher
    2.28
    櫚
    2.27
    玙
    2.27
    Act Density 0.001%

    No Known Activations