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

    Neuronpedia

    INDEX
    Explanations

    unlike many other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विविध
    0.48
    Different
    0.47
    different
    0.45
    Specific
    0.45
    specific
    0.44
    additional
    0.43
    anything
    0.42
    ayer
    0.42
     Different
    0.41
    pecific
    0.40
    POSITIVE LOGITS
     hasonló
    0.97
     similaires
    0.93
     similarly
    0.92
     similares
    0.91
     similar
    0.91
     podob
    0.89
     ähn
    0.89
     비슷한
    0.89
     подобных
    0.88
     подоб
    0.84
    Act Density 0.019%

    No Known Activations