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

    Neuronpedia

    INDEX
    Explanations

    sequences and structures in data or algorithms

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

    various technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     detalla
    -0.44
     Wicidata
    -0.44
     detallada
    -0.43
     anún
    -0.43
     Económica
    -0.42
     démission
    -0.42
    Transkript
    -0.42
     nocturno
    -0.41
     muebles
    -0.41
     réus
    -0.41
    POSITIVE LOGITS
     defStyleAttr
    0.57
     jPanel
    0.57
     EconPapers
    0.51
    ropshire
    0.50
    heritance
    0.48
    AnchorStyles
    0.48
     ModelExpression
    0.47
    thood
    0.47
    Hentet
    0.46
    ducer
    0.45
    Act Density 0.166%

    No Known Activations