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

    Neuronpedia

    INDEX
    Explanations

    cost expensive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fastball
    -0.07
     Dominion
    -0.07
    liž
    -0.06
    '></
    -0.06
    grad
    -0.06
     nrows
    -0.06
     Κο
    -0.06
    Verifier
    -0.06
    +</
    -0.06
     높은
    -0.06
    POSITIVE LOGITS
     gerçek
    0.07
    130
    0.06
    OUTH
    0.06
    .before
    0.06
    lanmış
    0.06
    entreprise
    0.06
     achieving
    0.06
    531
    0.06
    ことも
    0.06
    EncodingException
    0.06
    Act Density 0.019%

    No Known Activations