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

    Neuronpedia

    INDEX
    Explanations

    riddles or specific answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asing
    0.48
     digit
    0.47
     stripping
    0.44
     बिना
    0.44
    o
    0.43
     personal
    0.42
     vans
    0.42
     роди
    0.42
     lumped
    0.41
    nThe
    0.40
    POSITIVE LOGITS
    ১
    0.54
    を持っている
    0.52
    である
    0.51
     attivo
    0.51
    ત
    0.51
     miejsce
    0.50
     innymi
    0.50
    эт
    0.49
    બ
    0.49
    ર્
    0.49
    Act Density 0.001%

    No Known Activations