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

    Neuronpedia

    INDEX
    Explanations

    references to perception and observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Forms of "see"

    np_acts-logits-general · gemini-2.0-flash

    seeing or perception of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.60
     bezeichneter
    -0.60
     faptul
    -0.59
    DataAnnotations
    -0.56
    ArrowToggle
    -0.55
    idad
    -0.55
    bitat
    -0.54
    انيف
    -0.53
    ally
    -0.52
     թվական
    -0.51
    POSITIVE LOGITS
     sees
    0.90
     Sees
    0.89
    Saw
    0.88
     مشين
    0.85
    saw
    0.83
     how
    0.83
    RectangleBorder
    0.82
     glimpses
    0.80
     clearly
    0.76
     firsthand
    0.72
    Act Density 0.151%

    No Known Activations