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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    erest
    -0.74
    inar
    -0.69
     Berger
    -0.68
     Hamilton
    -0.66
    entious
    -0.64
    enhagen
    -0.62
    gallery
    -0.62
    arcity
    -0.61
    eers
    -0.60
     Huma
    -0.60
    POSITIVE LOGITS
     defe
    0.67
    Downloadha
    0.64
    xff
    0.63
     achievable
    0.62
    ionic
    0.60
    icol
    0.60
    æ°
    0.60
    Stat
    0.60
     activ
    0.60
     charging
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.