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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions relating to properties of sets, including their dimensions and relationships

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

    "is" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    is followed by descriptive properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unfamiliar
    -0.60
    cshtml
    -0.58
    +#+#
    -0.55
    낌
    -0.55
     Uncertain
    -0.55
     Pristupljeno
    -0.52
    unusual
    -0.52
     Compar
    -0.52
     grappling
    -0.52
     ungewöhn
    -0.51
    POSITIVE LOGITS
    ódó
    0.62
     brancas
    0.62
    Scénario
    0.60
     Puoi
    0.57
     Protestantism
    0.56
     eux
    0.55
     orina
    0.54
    LookAnd
    0.53
    ffindor
    0.53
     femei
    0.53
    Act Density 1.261%

    No Known Activations