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

    Neuronpedia

    INDEX
    Explanations

    medical implants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.87
     uſed
    -0.82
     houſe
    -0.80
     reaſon
    -0.76
     myſelf
    -0.75
     himſelf
    -0.73
     whoſe
    -0.73
     itſelf
    -0.73
     faſt
    -0.72
     ſtate
    -0.71
    POSITIVE LOGITS
    quelize
    0.73
     Audiodateien
    0.65
    #+#
    0.65
    AnchorTagHelper
    0.64
    سجيلات
    0.59
    tvguidetime
    0.56
    ullable
    0.54
    rifying
    0.54
    Facades
    0.53
    ių
    0.53
    Act Density 0.933%

    No Known Activations