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

    Neuronpedia

    INDEX
    Explanations

    Organizationally Unique Identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     semplice
    0.50
    یو
    0.43
    ೆಂ
    0.43
    simple
    0.43
     Standort
    0.42
    elow
    0.41
     aos
    0.40
     sencilla
    0.40
     simple
    0.40
    روی
    0.40
    POSITIVE LOGITS
    ielle
    0.51
    ální
    0.45
     algorithm
    0.43
    árs
    0.42
    álního
    0.42
    ванные
    0.41
     ор
    0.41
    öger
    0.41
    zné
    0.40
    ologist
    0.40
    Act Density 0.000%

    No Known Activations