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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Become
    -0.07
    arsi
    -0.07
    lient
    -0.07
    ✛
    -0.06
    丛林
    -0.06
    leşme
    -0.06
    riendly
    -0.06
    /Admin
    -0.06
    出于
    -0.06
    עבור
    -0.06
    POSITIVE LOGITS
    ition
    0.07
    .m
    0.07
     Cod
    0.07
    Credentials
    0.07
     Ginger
    0.07
     Met
    0.06
     photographer
    0.06
    ;s
    0.06
    들이
    0.06
    =("
    0.06
    Act Density 0.001%

    No Known Activations