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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    conserv
    -0.81
    omics
    -0.65
     olig
    -0.65
    ucle
    -0.64
     popul
    -0.64
     imm
    -0.63
     advoc
    -0.62
     fab
    -0.62
     Boh
    -0.61
    zon
    -0.61
    POSITIVE LOGITS
    20439
    0.75
     Explosive
    0.75
     Daylight
    0.71
    rocket
    0.69
     Uniform
    0.69
     curfew
    0.68
     deadlines
    0.65
     Everest
    0.64
    ļéĨĴ
    0.63
     Martian
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.