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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.75
    SHARE
    -0.75
    ronic
    -0.74
     Militia
    -0.71
    WI
    -0.69
    laugh
    -0.69
     Mutual
    -0.68
    Alert
    -0.67
     Volunteers
    -0.66
     Settlement
    -0.65
    POSITIVE LOGITS
    enhagen
    0.81
    ynes
    0.73
    rafted
    0.71
    atta
    0.70
     mango
    0.65
    isitions
    0.65
     aph
    0.64
    frames
    0.63
    ileaks
    0.63
    ojure
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.