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

    Neuronpedia

    INDEX
    Explanations

    psychological effects, aspects, and toll

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    0.74
    ний
    0.68
    <0xAF>
    0.67
    くちゃ
    0.65
    setter
    0.64
    venue
    0.63
    posición
    0.63
    stri
    0.62
    iéndose
    0.62
    tilde
    0.61
    POSITIVE LOGITS
    е
    0.82
     psychologists
    0.76
    _
    0.75
     psychologist
    0.73
     psychology
    0.72
    ม
    0.70
    ↵
    0.70
     Psychologist
    0.69
     психологи
    0.68
     Psychological
    0.68
    Act Density 0.017%

    No Known Activations