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

    Neuronpedia

    INDEX
    Explanations

    retrieval based on information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tok
    0.83
    Jean
    0.82
    Ott
    0.79
    panel
    0.78
    At
    0.76
    papier
    0.75
    Alpine
    0.75
    Infinity
    0.74
     sprem
    0.74
    Apart
    0.74
    POSITIVE LOGITS
     fyrir
    0.96
     according
    0.90
     Según
    0.88
    ToBounds
    0.87
    ⴹ
    0.87
     to
    0.86
     según
    0.84
     Matches
    0.82
    για
    0.82
     Για
    0.82
    Act Density 0.000%

    No Known Activations