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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    é¾įå¥ij士
    -0.75
    ãĤµ
    -0.73
    ãĥķ
    -0.71
    ONSORED
    -0.67
    çĭ
    -0.66
    emetery
    -0.66
    termination
    -0.64
    ral
    -0.64
    pected
    -0.63
    Roaming
    -0.63
    POSITIVE LOGITS
    yip
    0.80
    microsoft
    0.76
    itsch
    0.74
    ites
    0.70
    asca
    0.64
    atial
    0.63
     circles
    0.61
    iets
    0.60
    shire
    0.60
    iage
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.