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

    Neuronpedia

    INDEX
    Explanations

    agents: AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     பத
    0.50
     चौ
    0.47
    ım
    0.47
    n
    0.46
     ഇന്ത്യ
    0.46
     ಫ
    0.46
     Maugin
    0.46
    pawns
    0.45
    kun
    0.45
    mover
    0.44
    POSITIVE LOGITS
    䊂
    0.52
    راضي
    0.47
     multiplicado
    0.46
    Workshop
    0.45
    ríklad
    0.44
     Empresas
    0.43
     produzido
    0.43
     representado
    0.42
     satisfacción
    0.42
     Sess
    0.42
    Act Density 0.000%

    No Known Activations