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

    Neuronpedia

    INDEX
    Explanations

    value following number or symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bismarck
    0.77
    Ơ
    0.77
     Такой
    0.75
    卞
    0.75
     Некоторые
    0.72
    Пі
    0.71
     학
    0.69
     cumin
    0.69
     equate
    0.69
     посвя
    0.68
    POSITIVE LOGITS
    zione
    0.68
    vib
    0.62
    uie
    0.62
    spapers
    0.61
    ும்போது
    0.61
    fullpath
    0.61
    irà
    0.60
    bbe
    0.60
    ล่าสุด
    0.60
    scribe
    0.59
    Act Density 0.002%

    No Known Activations