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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    mob
    -0.68
     manure
    -0.65
     act
    -0.65
    izont
    -0.65
    bourg
    -0.65
     intensity
    -0.64
    aila
    -0.64
     receipt
    -0.63
    nergy
    -0.62
     creditor
    -0.61
    POSITIVE LOGITS
    anka
    0.70
    rez
    0.69
    etsk
    0.68
     Viktor
    0.68
    nik
    0.68
     Naj
    0.67
     mant
    0.67
     Seraph
    0.65
     Sergey
    0.65
    ÅĤ
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.