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

    Neuronpedia

    INDEX
    Explanations

    did the joke questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.69
     pre
    0.67
    ness
    0.67
    ris
    0.64
    ens
    0.62
     trials
    0.62
     ethn
    0.62
     interceptions
    0.62
     me
    0.61
     sap
    0.61
    POSITIVE LOGITS
    鉐
    0.93
     guerre
    0.92
     さらに
    0.89
    Пла
    0.88
    elemento
    0.83
    Usuario
    0.82
    iciente
    0.82
    usuario
    0.82
     Jeśli
    0.80
     Мето
    0.79
    Act Density 0.004%

    No Known Activations