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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ed
    0.81
    ות
    0.80
    s
    0.76
    de
    0.74
    record
    0.74
    run
    0.74
    dish
    0.70
    ens
    0.69
    rat
    0.69
    lah
    0.69
    POSITIVE LOGITS
     บ้าน
    0.79
     tuberculous
    0.77
     mínimo
    0.77
     gable
    0.77
    𝒜
    0.76
     Microsc
    0.75
     intellig
    0.72
     surfers
    0.71
     jóvenes
    0.71
     httpServer
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.