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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aing
    0.77
    stic
    0.72
    sts
    0.72
    msen
    0.72
     WIP
    0.69
     hairstyle
    0.68
    ensely
    0.68
    lte
    0.68
    ezing
    0.68
    रित
    0.67
    POSITIVE LOGITS
    अगर
    0.78
                   
    0.74
    Если
    0.72
    我
    0.72
    KL
    0.69
    CF
    0.67
     unavailable
    0.66
     Kembali
    0.66
    если
    0.65
     пи
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.