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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Balancer
    -0.08
     Successfully
    -0.07
    PKG
    -0.07
    (Class
    -0.07
     viscosity
    -0.07
     features
    -0.07
    💫
    -0.07
     Atlantic
    -0.07
     SOUR
    -0.07
     resultant
    -0.07
    POSITIVE LOGITS
    較
    0.07
    odata
    0.07
     Perm
    0.06
    verte
    0.06
    ,alpha
    0.06
     ¥
    0.06
    オス
    0.06
     showroom
    0.06
     helpless
    0.06
    (epoch
    0.06
    Act Density 0.120%

    No Known Activations