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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Thumbnails
    -0.76
     thor
    -0.65
     tro
    -0.63
    aders
    -0.62
     pursu
    -0.62
    footed
    -0.60
    atson
    -0.60
     tigers
    -0.60
     crabs
    -0.59
     Ny
    -0.58
    POSITIVE LOGITS
    FLAG
    0.75
    istor
    0.71
    DIR
    0.69
    CRIP
    0.69
    FIX
    0.68
    REF
    0.66
    BLIC
    0.64
    overty
    0.64
    LOCK
    0.64
    OFF
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.