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

    Neuronpedia

    INDEX
    Explanations

    statements about personal experiences or opinions

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

    spite of, consistent with, further noted, find that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⟬
    -0.68
     Italijanski
    -0.61
    riwal
    -0.58
    Rohy
    -0.57
    SequentialGroup
    -0.57
     AssemblyProduct
    -0.55
     ſind
    -0.55
     ་་
    -0.54
    lovakia
    -0.52
     ligiloj
    -0.52
    POSITIVE LOGITS
    ViewImports
    0.39
    Notae
    0.38
    ViewFeatures
    0.37
    ScopeManager
    0.35
    AndEndTag
    0.32
    IVEREF
    0.30
    WriteBarrier
    0.30
    expandindo
    0.30
     مؤرشف
    0.30
    WireFormatLite
    0.29
    Act Density 0.404%

    No Known Activations