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

    Neuronpedia

    INDEX
    Explanations

    financial investment actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    መሳሳይ
    0.43
    ช่วง
    0.41
    plaats
    0.41
    มาจาก
    0.40
    繼續
    0.40
    他們
    0.40
    一樣
    0.40
     কোম্পানির
    0.39
     जब
    0.39
    同じ
    0.38
    POSITIVE LOGITS
    వర
    0.42
    ष्टा
    0.41
     gé
    0.40
     dearly
    0.40
     unwittingly
    0.38
     wenig
    0.38
    enties
    0.37
     Pino
    0.37
     પરંતુ
    0.37
     diligent
    0.36
    Act Density 0.002%

    No Known Activations