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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and examples

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

    contrast and example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromnode
    -0.63
    EndContext
    -0.56
    SourceChecksum
    -0.52
     nadzieję
    -0.50
    ChildScrollView
    -0.48
     increí
    -0.47
    ImageContext
    -0.46
    complexContent
    -0.46
    adaptiveStyles
    -0.45
     raiſ
    -0.45
    POSITIVE LOGITS
    ubar
    0.40
    anne
    0.38
    ″]
    0.36
    plas
    0.36
     Kard
    0.35
    ByVersion
    0.35
    Ta
    0.35
    Odd
    0.34
     next
    0.34
    bast
    0.34
    Act Density 0.077%

    No Known Activations