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

    Neuronpedia

    INDEX
    Explanations

    varying speeds, spreads, trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     s
    0.50
     Metabolism
    0.48
    ®,
    0.46
    ,
    0.44
    *.
    0.44
    करण
    0.43
     plane
    0.43
     SAG
    0.43
     Treats
    0.43
     Analysis
    0.42
    POSITIVE LOGITS
    メイ
    0.49
    尽快
    0.44
    èn
    0.44
     attrezz
    0.43
    ட்க
    0.43
    Peri
    0.43
    setBorder
    0.43
    媺
    0.43
    থি
    0.42
    μών
    0.42
    Act Density 0.001%

    No Known Activations