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

    Neuronpedia

    INDEX
    Explanations

    the word "of" when it is used with 'all'

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.79
     NSCoder
    -0.75
     незавершена
    -0.69
     ProtoMessage
    -0.67
    LookAnd
    -0.66
     fubject
    -0.62
     betweenstory
    -0.62
     myſelf
    -0.61
     الاطلاع
    -0.60
     nakalista
    -0.60
    POSITIVE LOGITS
     sudden
    0.80
     Sudden
    0.63
    sud
    0.57
     suddenly
    0.52
    Sudden
    0.51
     nada
    0.49
     surprised
    0.47
     Suddenly
    0.44
     überrascht
    0.44
    äsent
    0.42
    Act Density 0.574%

    No Known Activations