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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ặ
    -0.07
    ⴷ
    -0.07
    𝙋
    -0.07
    珉
    -0.07
    乃
    -0.06
    Ϊ
    -0.06
    果实
    -0.06
    ABB
    -0.06
    (/
    -0.06
    ߤ
    -0.06
    POSITIVE LOGITS
     hoses
    0.07
     LDS
    0.07
     благод
    0.07
     Deploy
    0.07
    licer
    0.07
    活力
    0.07
     Lever
    0.07
    富民
    0.07
     Couldn
    0.07
     Ply
    0.07
    Act Density 0.127%

    No Known Activations