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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notation related to functions or algorithms

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

    Superscripted expressions, especially exponents

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions involving F, exponents, and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +:+
    -0.71
    UnknownFields
    -0.65
    TestingModule
    -0.64
    SharedDtor
    -0.63
    الإنجليزية
    -0.62
    invokeLater
    -0.60
    CppMethod
    -0.60
     DbSet
    -0.60
    TabIndex
    -0.59
     &___
    -0.58
    POSITIVE LOGITS
     lẫn
    0.51
     maupun
    0.43
    󠁢
    0.43
     thứ
    0.43
    umque
    0.42
    ,',
    0.42
    ADUATE
    0.41
    יתוף
    0.41
    dini
    0.41
    udayaan
    0.41
    Act Density 0.435%

    No Known Activations