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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     keywords
    0.59
     screwdriver
    0.56
     wafer
    0.55
     mass
    0.53
     kidney
    0.52
     wavelength
    0.50
     penthouse
    0.50
     houseboat
    0.50
     storage
    0.50
     lineage
    0.50
    POSITIVE LOGITS
    كيف
    0.56
    ח
    0.55
    im
    0.54
    د
    0.54
    את
    0.54
    الإ
    0.50
    ة
    0.49
    ص
    0.48
    ד
    0.48
    ن
    0.48
    Act Density 0.000%

    No Known Activations