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

    Neuronpedia

    INDEX
    Explanations

    Go followed by various words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TInner
    0.39
    পু
    0.38
    ক্ষণে
    0.38
    礡
    0.36
     ObjectMapper
    0.36
     जा
    0.36
    ទៅ
    0.36
     Regarding
    0.36
    ué
    0.34
    陬
    0.34
    POSITIVE LOGITS
    Go
    0.68
    FundMe
    0.66
     Go
    0.59
     го
    0.55
    VERNMENT
    0.54
    alkeeper
    0.54
    ogo
    0.53
    alke
    0.53
     goc
    0.52
     ゴ
    0.52
    Act Density 0.018%

    No Known Activations