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

    Neuronpedia

    INDEX
    Explanations

    physical actions and proximity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perpetuity
    0.67
     perpetuated
    0.65
     vacations
    0.64
    きたいと思います
    0.64
     priori
    0.64
     continuum
    0.64
     disseminated
    0.63
     mucosa
    0.62
     ساف
    0.62
    ༌
    0.62
    POSITIVE LOGITS
     briefly
    0.96
     beside
    0.85
     suddenly
    0.83
     again
    0.77
     momentarily
    0.76
     behind
    0.76
     Briefly
    0.76
     slightly
    0.75
     closer
    0.70
     abruptly
    0.69
    Act Density 0.085%

    No Known Activations