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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notations involving variables and their powers

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

    Mathematical expressions with symbols and numbers

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cr
    -0.58
    chanical
    -0.55
     cr
    -0.51
    iotensin
    -0.51
     Henry
    -0.49
    DebuggerNonUser
    -0.49
    тя
    -0.49
    arj
    -0.49
    пя
    -0.48
    ǒ
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.86
     betweenstory
    0.84
    StoryboardSegue
    0.80
     externi
    0.75
    saraba
    0.73
    ValueStyle
    0.73
    thée
    0.73
     незавершена
    0.72
    المناصب
    0.71
    makeConstraints
    0.70
    Act Density 0.899%

    No Known Activations