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

    Neuronpedia

    INDEX
    Explanations

    certain instance or statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getSimple
    0.63
     entrambe
    0.61
    Anche
    0.60
     begge
    0.60
    ğmen
    0.60
    Both
    0.58
    Auch
    0.58
    两者
    0.57
    Cxx
    0.57
    fdPar
    0.57
    POSITIVE LOGITS
     certains
    0.83
     certain
    0.82
     suitcases
    0.81
     certaines
    0.75
     Certain
    0.70
     ciertos
    0.70
     certaine
    0.70
     plupart
    0.69
     começo
    0.69
     thousands
    0.66
    Act Density 0.000%

    No Known Activations