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

    Neuronpedia

    INDEX
    Explanations

    As an AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mentioned
    1.02
     said
    0.97
     oben
    0.92
     stated
    0.89
     already
    0.89
     aforesaid
    0.84
     уже
    0.82
     noted
    0.81
     Said
    0.80
     zaten
    0.79
    POSITIVE LOGITS
    yourself
    0.76
    できる
    0.75
    如果我们
    0.74
    Sebagai
    0.72
    Hãy
    0.72
     ব্যস্ত
    0.72
     meticulous
    0.71
    ucidation
    0.70
    çük
    0.69
     véritable
    0.69
    Act Density 0.015%

    No Known Activations