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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating calculations or mathematical expressions

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

    Followed by a number

    np_acts-logits-general · gemini-2.0-flash

    Saved me or find calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BorderRadius
    -0.63
    וויק
    -0.60
    BeginContext
    -0.58
    AxisAlignment
    -0.58
     ویکی‌آمباردا
    -0.56
    InitVars
    -0.56
     متعلقه
    -0.52
    تقاوى
    -0.52
    PageIndex
    -0.50
    MemoryWarning
    -0.49
    POSITIVE LOGITS
    openzeppelin
    0.58
    المناصب
    0.53
     surfactant
    0.50
     wronged
    0.50
    сль
    0.50
     reactants
    0.50
    WERS
    0.49
     Rican
    0.49
     appendages
    0.48
    ingga
    0.48
    Act Density 0.910%

    No Known Activations