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

    Neuronpedia

    INDEX
    Explanations

    eny

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eny
    -0.87
    elson
    -0.63
    bbene
    -0.61
     vermelhas
    -0.61
     Chriftian
    -0.59
    ilah
    -0.58
     feveral
    -0.58
     Theſe
    -0.58
    enterOuterAlt
    -0.57
     Jefus
    -0.56
    POSITIVE LOGITS
    +#+#
    0.60
    parsedMessage
    0.58
     שוליים
    0.57
     تانيه
    0.56
     forno
    0.50
    topo
    0.47
     Hig
    0.47
     numerus
    0.46
     Sabha
    0.46
     oprot
    0.45
    Act Density 0.070%

    No Known Activations