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

    Neuronpedia

    INDEX
    Explanations

    buy, beat, or generations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rate
    0.47
     timestamp
    0.42
    rate
    0.41
     Rate
    0.40
    mr
    0.39
     rates
    0.38
    Berry
    0.37
    лава
    0.37
    стые
    0.36
     hous
    0.36
    POSITIVE LOGITS
    賢
    0.44
    멋
    0.44
    нцип
    0.43
     lepiej
    0.43
     zusätzlichen
    0.42
     멋
    0.42
     دلیل
    0.41
    醎
    0.39
     συμπ
    0.39
     примеру
    0.38
    Act Density 0.000%

    No Known Activations