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

    Neuronpedia

    INDEX
    Explanations

    physical actions and abilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hibernate
    0.41
    <_
    0.38
     Tell
    0.37
     vacation
    0.36
     seasoned
    0.36
     給
    0.36
     }_{\
    0.36
     काबिल
    0.36
     Hib
    0.36
     Allowing
    0.36
    POSITIVE LOGITS
    Standing
    0.83
     standing
    0.78
     debout
    0.77
    standing
    0.72
     Standing
    0.72
     berdiri
    0.71
     walking
    0.68
    walking
    0.64
     kneeling
    0.63
     physically
    0.63
    Act Density 0.008%

    No Known Activations