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

    Neuronpedia

    INDEX
    Explanations

    code execution of commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     của
    0.45
     của
    0.45
    j
    0.44
     of
    0.43
     Conley
    0.43
     zrobić
    0.42
     ഓഫ്
    0.42
    ...),
    0.42
     Solskjaer
    0.42
     Malcolm
    0.41
    POSITIVE LOGITS
    ;
    0.55
    ();
    0.51
    ﺸ
    0.44
     partidas
    0.43
     intentos
    0.43
     serait
    0.42
     força
    0.42
     orbits
    0.41
     anivers
    0.41
     esfuerzos
    0.40
    Act Density 0.026%

    No Known Activations