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

    Neuronpedia

    INDEX
    Explanations

    large numbers calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ל
    0.79
    ما
    0.75
    ور
    0.70
    CONFIG
    0.70
    ла
    0.67
    مل
    0.67
    ل
    0.67
    ה
    0.66
    ς
    0.66
    ים
    0.66
    POSITIVE LOGITS
     sini
    0.63
     bea
    0.63
     motorcycle
    0.61
     sixth
    0.60
     tredje
    0.60
     шокола
    0.59
     in
    0.59
     pathway
    0.59
     organiza
    0.59
     unite
    0.59
    Act Density 0.000%

    No Known Activations