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

    Neuronpedia

    INDEX
    Explanations

    detailed explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     commemorates
    0.52
     Sachsen
    0.50
     kingdoms
    0.50
     Bremen
    0.49
     complicate
    0.49
    न
    0.49
     commemorating
    0.48
     jez
    0.47
     metode
    0.46
     fundación
    0.46
    POSITIVE LOGITS
    ての
    0.44
    तः
    0.43
    㿟
    0.42
    𝙵
    0.41
    zA
    0.41
    жность
    0.41
    uctance
    0.41
    擞
    0.41
     khổ
    0.40
    鲈
    0.40
    Act Density 0.000%

    No Known Activations