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

    Neuronpedia

    INDEX
    Explanations

    person or animal acting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ничек
    0.72
    ụn
    0.71
     toxicity
    0.69
     gelişt
    0.69
    ಗೂ
    0.68
     inasmuch
    0.68
     عايزين
    0.67
     empirical
    0.67
     perkembangan
    0.66
     develop
    0.66
    POSITIVE LOGITS
     standing
    2.30
     sitting
    1.98
     seated
    1.88
     wearing
    1.87
     smiling
    1.86
     holding
    1.84
     kneeling
    1.83
    Standing
    1.83
     gazing
    1.82
     Standing
    1.81
    Act Density 0.389%

    No Known Activations