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

    Neuronpedia

    INDEX
    Explanations

    heavy lifting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     délais
    0.41
     cramped
    0.40
     bounce
    0.39
     clog
    0.38
    DomainMask
    0.38
     lucrat
    0.38
     Cutter
    0.38
     estrat
    0.37
    ɖ
    0.37
     volatile
    0.37
    POSITIVE LOGITS
     lifting
    0.66
     mengangkat
    0.64
    lifting
    0.61
     exertion
    0.58
     Lifting
    0.57
     lifts
    0.56
    lifts
    0.55
     exertions
    0.55
    Lift
    0.54
     Objects
    0.53
    Act Density 0.006%

    No Known Activations