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

    Neuronpedia

    INDEX
    Explanations

    numbered lists or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mata
    1.39
     baan
    1.38
    -
    1.35
     причиной
    1.34
     WB
    1.33
     organisers
    1.32
     unes
    1.32
    -...
    1.31
     éxito
    1.30
    照
    1.30
    POSITIVE LOGITS
    4
    2.61
    3
    2.55
    5
    2.54
    8
    2.54
    7
    2.50
    6
    2.49
    2
    2.33
    9
    2.32
    1
    2.04
    0
    1.83
    Act Density 0.085%

    No Known Activations