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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and expressions related to statistical distributions and operations

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

    Mathematical expressions with parentheses and symbols

    np_acts-logits-general · gemini-2.0-flash

    `big` following closing brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.77
    CppMethod
    -0.59
     mukana
    -0.52
    Geplaatst
    -0.51
    $.}
    -0.49
    /******/
    -0.48
    هو
    -0.47
     Rous
    -0.46
    المشاركات
    -0.46
     haline
    -0.45
    POSITIVE LOGITS
     ProtoMessage
    0.67
     الحره
    0.65
     himo
    0.62
    gwt
    0.59
    ukone
    0.53
    FactoryBean
    0.52
    right
    0.51
    0.51
    PasswordEncoder
    0.51
    Witam
    0.50
    Act Density 1.084%

    No Known Activations