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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by time units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stylu
    0.74
     하나의
    0.70
    刚才
    0.69
    ணும்
    0.68
    呮
    0.68
    stuff
    0.67
    第二次
    0.67
    fcntl
    0.67
     çap
    0.66
    tAux
    0.66
    POSITIVE LOGITS
     weeks
    4.38
     months
    3.77
    weeks
    3.63
     Weeks
    3.56
     days
    3.44
     Months
    3.37
    Weeks
    3.37
     semanas
    3.30
    months
    3.23
     settimane
    3.03
    Act Density 0.550%

    No Known Activations