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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    can
    1.19
    is
    1.15
    users
    1.13
    z
    1.13
    de
    1.12
    tin
    1.12
    m
    1.08
    and
    1.07
    sa
    1.06
    a
    1.06
    POSITIVE LOGITS
     다른
    0.79
     크
    0.79
     ditem
    0.76
     차량
    0.76
     독일
    0.74
     nausea
    0.73
     nécessairement
    0.71
     Standort
    0.70
     krank
    0.70
     thermoplastic
    0.69
    Act Density 0.000%

    No Known Activations