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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    IELD
    -0.74
    rollers
    -0.69
    ocity
    -0.69
     lanes
    -0.68
     Amend
    -0.61
    çĶ°
    -0.61
    Scale
    -0.60
     flesh
    -0.59
    });
    -0.59
    roller
    -0.58
    POSITIVE LOGITS
     reflection
    0.77
     virtue
    0.70
    unicip
    0.70
    uting
    0.69
    hist
    0.68
    uct
    0.68
    robe
    0.67
     whiff
    0.66
    Spoiler
    0.65
    Magikarp
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.