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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bikes
    1.04
     Maar
    1.02
     Ș
    0.98
     време
    0.98
    TST
    0.97
    сах
    0.96
    messer
    0.94
    𝗦
    0.93
    cijas
    0.93
    हालांकि
    0.92
    POSITIVE LOGITS
    ie
    0.79
    in
    0.77
     輸入
    0.74
     deps
    0.72
    ையாள
    0.71
    ge
    0.70
    early
    0.70
     Introductory
    0.70
    understood
    0.69
    descriptor
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.