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

    Neuronpedia

    INDEX
    Explanations

    expressions related to watching or viewing activities

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

    watch and see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esterni
    -0.59
     الرياضيه
    -0.56
     transférez
    -0.55
     TestBed
    -0.52
     Bourgoin
    -0.52
     ويكيميديا
    -0.52
     Roskov
    -0.51
     nakalista
    -0.50
    vres
    -0.49
    ttino
    -0.48
    POSITIVE LOGITS
     seeing
    0.56
     Seeing
    0.55
    看
    0.48
    seeing
    0.48
     看
    0.47
    Seeing
    0.47
    看你
    0.46
    看到
    0.46
     see
    0.45
     See
    0.45
    Act Density 0.007%

    No Known Activations