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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pty
    -0.75
    nces
    -0.74
    wl
    -0.68
    figure
    -0.68
     looph
    -0.66
    PDATE
    -0.64
     juveniles
    -0.64
     disproportion
    -0.63
    quished
    -0.63
    istors
    -0.63
    POSITIVE LOGITS
    aer
    0.72
    roth
    0.70
     Gleaming
    0.67
    sson
    0.66
    Ò
    0.66
     guiActiveUnfocused
    0.64
     Kend
    0.63
    Relations
    0.63
     Scully
    0.62
     Goldberg
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.