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

    Neuronpedia

    INDEX
    Explanations

    references to external links and instances of denial or disagreement

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

    いや

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.41
    mbggenerated
    -0.40
    ViewImports
    -0.39
    oneofs
    -0.39
    RTEX
    -0.36
    んでも
    -0.36
     actuar
    -0.35
     Unido
    -0.35
     varietà
    -0.35
    enumi
    -0.34
    POSITIVE LOGITS
     lä
    2.13
    Lä
    1.55
     Lä
    1.55
    lä
    1.21
     læ
    0.82
    læ
    0.65
    läge
    0.64
    LÄ
    0.64
    läg
    0.59
     Photocase
    0.56
    Act Density 0.004%

    No Known Activations