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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe positions, roles, or designations in various contexts

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

    article followed by noun phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.48
     resourceCulture
    -0.44
    EDEFAULT
    -0.41
     ویکی‌پدیای
    -0.40
     leads
    -0.35
    CppMethod
    -0.35
    belea
    -0.34
     responsible
    -0.34
    Ketua
    -0.34
     Responsible
    -0.34
    POSITIVE LOGITS
    \{\\
    0.51
     незавершена
    0.48
     spéciales
    0.47
    SharedCtor
    0.47
    oplasts
    0.46
    kémon
    0.44
    ihnachts
    0.43
     atmosf
    0.43
    ihnachten
    0.42
    ๆ
    0.42
    Act Density 0.100%

    No Known Activations