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

    Neuronpedia

    INDEX
    Explanations

    medical procedures, biological sex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     незавершена
    -0.83
     pleaſure
    -0.78
     ſeveral
    -0.71
     Monfieur
    -0.71
     purpoſe
    -0.69
     uſe
    -0.69
     itſelf
    -0.68
     themſelves
    -0.67
     reaſon
    -0.67
     sexes
    -0.66
    POSITIVE LOGITS
     stud
    0.47
     en
    0.44
    KeyPair
    0.44
     Governor
    0.43
    ंदीखरीदारी
    0.42
    Referències
    0.41
    att
    0.41
    Governor
    0.41
    Zj
    0.40
     em
    0.39
    Act Density 0.978%

    No Known Activations