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

    Neuronpedia

    INDEX
    Explanations

    arrange, put, replace, pass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     활용
    0.56
     conviv
    0.53
     éduc
    0.52
     interwoven
    0.49
     avantages
    0.48
     metaverse
    0.47
     preuves
    0.47
    ્રોલ
    0.45
    檛
    0.45
    знав
    0.45
    POSITIVE LOGITS
    4
    0.75
    the
    0.68
    3
    0.66
    8
    0.64
    ﺔ
    0.64
     Cũng
    0.60
    ﺎ
    0.60
     the
    0.59
     también
    0.58
    6
    0.58
    Act Density 1.395%

    No Known Activations