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

    Neuronpedia

    INDEX
    Explanations

    technical terms and criteria related to medical and regulatory guidelines

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

    "Or" followed by a synonym or related word

    np_acts-logits-general · gemini-2.0-flash

    introducing alternatives or replacements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rag
    -0.33
     contamin
    -0.32
     stages
    -0.31
     disc
    -0.29
     Mao
    -0.29
    ╗
    -0.29
     brass
    -0.29
     tam
    -0.29
     Dumas
    -0.29
     reg
    -0.28
    POSITIVE LOGITS
     snippetHide
    0.71
    saraba
    0.70
    setHorizontal
    0.68
    alternative
    0.64
     alternative
    0.63
     alternativas
    0.60
    awtextra
    0.60
     alternatively
    0.58
     alternatives
    0.57
    ंदीखरीदारी
    0.57
    Act Density 0.539%

    No Known Activations