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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.07
    3:0.07
    4:0.08
    5:0.09
    6:0.08
    7:0.09
    8:0.09
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
     Ung
    -1.65
    lycer
    -1.63
     cous
    -1.56
     Dill
    -1.54
    chool
    -1.54
    IFE
    -1.53
    uncture
    -1.52
     bribes
    -1.51
     Balk
    -1.50
    ernels
    -1.48
    POSITIVE LOGITS
    else
    1.65
     ultraviolet
    1.57
    endif
    1.54
    radio
    1.36
    sound
    1.35
     emergencies
    1.34
    {"
    1.32
    priority
    1.31
     WATCH
    1.31
    },"
    1.31
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.