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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and related expressions

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

    Third derivative calculations

    np_acts-logits-general · gemini-2.0-flash

    calculating mathematical derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addComponent
    -0.49
    ‐
    -0.48
     cum
    -0.48
     plus
    -0.48
    <sup>
    -0.48
    ...@
    -0.47
     hereby
    -0.45
     monte
    -0.45
    тивно
    -0.45
     + 
    -0.44
    POSITIVE LOGITS
     Monfieur
    0.86
     '\\;'
    0.80
     ainfi
    0.78
    DebuggerStep
    0.78
     itſelf
    0.76
     myſelf
    0.74
     pioggia
    0.74
     becauſe
    0.72
     iſt
    0.72
     whoſe
    0.71
    Act Density 3.784%

    No Known Activations