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

    Neuronpedia

    INDEX
    Explanations

    sharing knowledge, experiences, and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Когда
    0.42
     لها
    0.41
     لأ
    0.40
    要求
    0.40
     ايه
    0.40
    产品
    0.39
     ద్వారా
    0.39
    眝
    0.38
     اړه
    0.38
     satisfiable
    0.38
    POSITIVE LOGITS
     sharing
    0.88
     share
    0.88
     condiv
    0.82
     compartilhar
    0.81
    Sharing
    0.80
     Sharing
    0.79
     partager
    0.78
     shared
    0.75
     compartir
    0.74
     compartilh
    0.73
    Act Density 0.016%

    No Known Activations