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

    Neuronpedia

    INDEX
    Explanations

    dialogue punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     novela
    -0.94
    vater
    -0.93
     februari
    -0.85
     pembun
    -0.84
     votre
    -0.82
     previa
    -0.81
     creators
    -0.81
     regulators
    -0.80
    ]))
    -0.79
    医生
    -0.78
    POSITIVE LOGITS
     another
    1.03
    ΡΙ
    0.98
    IELD
    0.95
     dirigió
    0.93
    "$_
    0.91
     meinte
    0.90
    ènement
    0.90
    PARATUS
    0.88
    assertIn
    0.87
    řit
    0.86
    Act Density 0.012%

    No Known Activations