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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    get
    0.94
     exalted
    0.91
    dx
    0.88
    &
    0.88
    nginx
    0.88
    cf
    0.82
    /)
    0.82
    %).
    0.80
    이번
    0.80
    ?,?,
    0.80
    POSITIVE LOGITS
    uminum
    1.02
    㬹
    1.01
    므
    0.99
     Außerdem
    0.98
     utilisée
    0.96
     pelajaran
    0.95
    装
    0.93
    楝
    0.93
     Trevor
    0.92
     Cognitive
    0.91
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.