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

    Neuronpedia

    INDEX
    Explanations

    discussions around terms related to criticism and distinctions in topics

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

    technical points and semantics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.54
     كومونز
    -0.50
    colgroup
    -0.50
    fromnode
    -0.49
    WriteTagHelper
    -0.46
    Hochspringen
    -0.45
    Skocz
    -0.44
    AsUp
    -0.44
     disponibilités
    -0.42
    complexContent
    -0.41
    POSITIVE LOGITS
     technical
    0.51
     picky
    0.47
     counting
    0.44
     semantic
    0.44
     Semantics
    0.44
     Counting
    0.43
     Technical
    0.43
     preci
    0.42
    pples
    0.42
     TECHNICAL
    0.41
    Act Density 0.307%

    No Known Activations