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

    Neuronpedia

    INDEX
    Explanations

    references to invisibility or states of being unseen

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

    invisible things and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     romantique
    -0.63
     époux
    -0.60
     betreft
    -0.60
     romántica
    -0.59
     vastaan
    -0.58
     sentito
    -0.57
    paikan
    -0.56
     estadounid
    -0.54
     kasarigan
    -0.54
     الرياضيه
    -0.54
    POSITIVE LOGITS
     invisible
    2.22
     Invisible
    2.16
    invisible
    2.13
    Invisible
    2.08
     invis
    1.79
    INVISIBLE
    1.50
     Invis
    1.46
     unseen
    1.27
     hidden
    1.04
     Hidden
    0.99
    Act Density 0.006%

    No Known Activations