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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     taxp
    -0.77
     Geral
    -0.70
     lawy
    -0.69
     Jed
    -0.69
    natureconservancy
    -0.68
     unres
    -0.66
     captcha
    -0.64
    intestinal
    -0.64
     uncond
    -0.64
    soDeliveryDate
    -0.63
    POSITIVE LOGITS
    adr
    0.84
    ace
    0.70
    AMI
    0.70
    unda
    0.64
    dr
    0.62
    genre
    0.62
    abal
    0.62
    hower
    0.61
    bler
    0.60
    OSS
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.