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

    Neuronpedia

    INDEX
    Explanations

    enjoyable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lähteet
    -0.85
    Viited
    -0.74
    VersionUID
    -0.73
    ]--;
    -0.73
    ParallelGroup
    -0.65
    BeginContext
    -0.64
    verifyException
    -0.62
    NUMX
    -0.61
     Italijani
    -0.60
    UnitTesting
    -0.57
    POSITIVE LOGITS
     thì
    0.56
     yet
    0.52
     could
    0.50
    jalá
    0.48
     zijn
    0.47
     would
    0.47
    ม้
    0.46
    yet
    0.46
    TRAILING
    0.44
     μπο
    0.44
    Act Density 0.006%

    No Known Activations