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

    Neuronpedia

    INDEX
    Explanations

    nuanced perspective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pulse
    0.49
     Muscle
    0.44
     Explor
    0.44
     Rud
    0.43
     During
    0.43
     Obtain
    0.43
     Added
    0.43
     during
    0.43
     added
    0.42
     multi
    0.42
    POSITIVE LOGITS
     言っ
    0.58
    タイトル
    0.52
    ጠት
    0.52
     positivos
    0.50
    tablename
    0.49
    тив
    0.48
    ্লে
    0.48
    ле
    0.48
     истины
    0.48
     пози
    0.48
    Act Density 0.097%

    No Known Activations