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

    Neuronpedia

    INDEX
    Explanations

    voluntary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    possible
    -0.08
     Pant
    -0.08
    ward
    -0.07
    agrance
    -0.07
     numer
    -0.07
    최
    -0.07
     kehidupan
    -0.07
     MAD
    -0.07
    urrent
    -0.07
    SH
    -0.06
    POSITIVE LOGITS
     voluntarily
    0.14
     voluntary
    0.12
     willingly
    0.12
     volunt
    0.10
     freiwill
    0.09
     түрде
    0.09
     volunteering
    0.09
     volontaire
    0.09
     relinqu
    0.08
    เลือก
    0.08
    Act Density 0.012%

    No Known Activations