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

    Neuronpedia

    INDEX
    Explanations

    home or office; when there

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     while
    0.48
    のように
    0.46
     enquanto
    0.45
     sambil
    0.42
    ldecode
    0.42
    бок
    0.41
    while
    0.40
     whilst
    0.40
     mientras
    0.39
     như
    0.38
    POSITIVE LOGITS
     visiting
    0.69
     celebrating
    0.63
     resting
    0.62
     studying
    0.61
     lounging
    0.59
     investigating
    0.57
    resting
    0.55
     exercising
    0.53
     partying
    0.53
    Visiting
    0.51
    Act Density 0.008%

    No Known Activations