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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    erker
    -0.84
    ptin
    -0.76
    starter
    -0.71
    enhagen
    -0.71
    uckles
    -0.71
    senal
    -0.70
    cin
    -0.69
    rencies
    -0.68
    obal
    -0.68
    sticks
    -0.67
    POSITIVE LOGITS
    yard
    0.66
     Nept
    0.61
     Yamato
    0.60
     crim
    0.59
     relatives
    0.59
     ILCS
    0.59
    ittal
    0.58
    jing
    0.57
     specification
    0.56
    ģĸ
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.