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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong opinions or criticisms

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

    strong opinions or statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.49
    发表于
    -0.42
    findpost
    -0.40
     <=",
    -0.38
    시오
    -0.36
    Helping
    -0.35
    ReusableCell
    -0.34
    TRAILING
    -0.33
     ISD
    -0.33
    ropriate
    -0.32
    POSITIVE LOGITS
    awaiter
    0.52
    acamata
    0.52
     promising
    0.47
     ComVisible
    0.45
    rowable
    0.45
     avancée
    0.44
     funcionales
    0.44
    inalg
    0.44
     formidable
    0.43
     remarqu
    0.43
    Act Density 0.124%

    No Known Activations