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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     articoli
    0.96
     alegr
    0.86
     produse
    0.86
     dando
    0.84
     grafica
    0.84
     printemps
    0.83
    𝐎
    0.83
     deixando
    0.82
     komen
    0.82
     kert
    0.82
    POSITIVE LOGITS
    יים
    0.75
    y
    0.69
    Mathematical
    0.68
    <0x0D>
    0.62
     mathematical
    0.60
     understatement
    0.59
    iec
    0.59
     Mathematical
    0.59
     האי
    0.57
    tree
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.