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

    Neuronpedia

    INDEX
    Explanations

    learning and discussion contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    عند
    0.47
     during
    0.45
     DURING
    0.44
    during
    0.43
     Podczas
    0.43
     when
    0.43
     Barcelona
    0.41
     Pos
    0.41
    Pos
    0.40
    when
    0.40
    POSITIVE LOGITS
     también
    0.48
     sociaux
    0.46
     aclar
    0.45
     tambien
    0.44
     compart
    0.44
     calendrier
    0.43
     inboard
    0.43
    非常的
    0.43
     alerta
    0.43
     modèles
    0.42
    Act Density 0.007%

    No Known Activations