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

    Neuronpedia

    INDEX
    Explanations

    names, places, or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    रेज
    0.26
    zovaniyu
    0.23
     τρόπο
    0.22
    敉
    0.21
     PROBLEMS
    0.21
    Variance
    0.21
    ጋገብ
    0.21
    betriebnahme
    0.21
     गेंदबाजों
    0.21
    合せ
    0.21
    POSITIVE LOGITS
     B
    0.28
     S
    0.28
     K
    0.26
     L
    0.26
     D
    0.25
     St
    0.25
     M
    0.25
     C
    0.25
    ena
    0.25
     V
    0.24
    Act Density 0.104%

    No Known Activations