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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    imate
    0.91
    nder
    0.85
    ofe
    0.84
    lor
    0.84
    ote
    0.83
    arge
    0.83
    e
    0.83
    fes
    0.82
    ective
    0.82
    ي
    0.82
    POSITIVE LOGITS
     postdoc
    1.00
    ന്തപു
    0.86
     brisket
    0.84
     चोपड़ा
    0.83
     депозиттик
    0.81
    诞生
    0.79
     malnourished
    0.79
     थोरो
    0.78
     triglycerides
    0.78
     βοη
    0.77
    Act Density 0.000%

    No Known Activations