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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Narc
    -0.76
     Anim
    -0.75
     Tactics
    -0.75
     Nights
    -0.71
    heit
    -0.69
    nance
    -0.65
     Civic
    -0.65
     Brotherhood
    -0.64
     anim
    -0.63
     Carib
    -0.63
    POSITIVE LOGITS
    rees
    0.83
    ̶
    0.81
    AFTA
    0.78
    olesterol
    0.71
    DI
    0.71
    apest
    0.70
    ALL
    0.68
    ugi
    0.68
    waukee
    0.68
    inventoryQuantity
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.