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

    Neuronpedia

    INDEX
    Explanations

    relationships and comparisons within broader concepts

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

    in relation to context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.40
    uroy
    -0.37
    ABASES
    -0.37
    bels
    -0.35
    DATABASES
    -0.35
    ugd
    -0.35
    entur
    -0.34
    erval
    -0.34
     재
    -0.34
     relieved
    -0.34
    POSITIVE LOGITS
     فريبيس
    0.59
     <<<<<<<<<<<<<<
    0.52
    0.46
     Réponses
    0.44
    AnchorTagHelper
    0.44
    BagConstraints
    0.44
     internationaux
    0.44
    transQ
    0.44
     forhold
    0.43
     berdua
    0.42
    Act Density 0.072%

    No Known Activations