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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Motor
    -0.07
    断裂
    -0.07
    double
    -0.07
     Ald
    -0.07
    .wind
    -0.06
    Lit
    -0.06
     enlightened
    -0.06
     vary
    -0.06
    aired
    -0.06
     люди
    -0.06
    POSITIVE LOGITS
    ⓙ
    0.07
    町
    0.07
    Ҽ
    0.07
    .panelControl
    0.06
    רש
    0.06
    etsk
    0.06
     recommendation
    0.06
     pacman
    0.06
     wicht
    0.06
    庵
    0.06
    Act Density 0.000%

    No Known Activations