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

    Neuronpedia

    INDEX
    Explanations

    references to specific subjects or objects in a discussion

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

    it is / this is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inā
    -0.38
    estacks
    -0.35
    geny
    -0.35
    |<\
    -0.34
    ври
    -0.34
    innis
    -0.34
    CppCodeGen
    -0.33
    |+\
    -0.33
     понятия
    -0.33
     Separate
    -0.33
    POSITIVE LOGITS
    endphp
    0.63
    0.60
    BASEPATH
    0.56
    ThroughAttribute
    0.56
    mphony
    0.54
     صوتيه
    0.54
    WebElementEntity
    0.52
    SourceChecksum
    0.50
    writeFieldEnd
    0.50
     pouvoit
    0.48
    Act Density 0.027%

    No Known Activations