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

    Neuronpedia

    INDEX
    Explanations

    elements related to medical treatment and dosing information

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

    simplification or reduction

    np_acts-logits-general · gemini-2.0-flash

    simplification and reduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ">//
    -0.45
    NewGuid
    -0.44
    awaiter
    -0.42
    AddAttribute
    -0.42
     Chwiliwch
    -0.40
    ram
    -0.39
     hostages
    -0.38
    Traceback
    -0.38
    iação
    -0.38
    lee
    -0.37
    POSITIVE LOGITS
     simplifies
    0.96
     simplify
    0.92
     simplification
    0.91
     fewer
    0.89
     reduced
    0.89
     Fewer
    0.88
    不需要
    0.88
     simplified
    0.87
     simpler
    0.87
     simplifying
    0.86
    Act Density 0.568%

    No Known Activations