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

    Neuronpedia

    INDEX
    Explanations

    container_name:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    0.46
     devient
    0.46
     engend
    0.44
     ой
    0.44
     exige
    0.44
    a
    0.43
     prenn
    0.43
    algèbre
    0.43
     imagina
    0.43
     recherche
    0.42
    POSITIVE LOGITS
     Опреде
    0.49
     Є
    0.48
    är
    0.46
    änd
    0.46
     Y
    0.46
    েন্ড
    0.44
    Gü
    0.43
     fuelwood
    0.43
    その
    0.42
     Süd
    0.42
    Act Density 0.000%

    No Known Activations