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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     recursive
    0.54
    Pentru
    0.50
    奈川
    0.47
     ric
    0.47
    ForRule
    0.47
    Pokud
    0.47
     Singular
    0.46
     felony
    0.46
    Neurons
    0.46
    cısı
    0.45
    POSITIVE LOGITS
    o
    0.64
    ing
    0.63
    formerly
    0.57
    ed
    0.55
    𝐧
    0.54
    he
    0.52
    ch
    0.52
    j
    0.52
     өл
    0.52
    ell
    0.51
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.