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

    Neuronpedia

    INDEX
    Explanations

    say "willing"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .fragment
    -0.07
    �
    -0.07
     आवश
    -0.06
     hashes
    -0.06
    фт
    -0.06
     tokenId
    -0.06
    PropertyName
    -0.06
     abaixo
    -0.06
     Hawai
    -0.06
    emploi
    -0.06
    POSITIVE LOGITS
    -request
    0.06
    .rabbit
    0.06
     reductions
    0.06
    既
    0.06
     never
    0.06
     Λα
    0.06
     fmt
    0.06
     Μαρ
    0.06
    reading
    0.06
     CONT
    0.06
    Act Density 0.153%

    No Known Activations