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

    Neuronpedia

    INDEX
    Explanations

    hereby [formal action]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     컨트롤
    1.03
    ងឺ
    0.99
    و
    0.99
    quela
    0.93
    ن
    0.91
    Variance
    0.90
    뷰
    0.90
    Valve
    0.89
    𒊑
    0.88
    Forg
    0.88
    POSITIVE LOGITS
     invaluable
    0.99
     explosives
    0.96
     mow
    0.91
    꿋
    0.90
     aquatic
    0.90
    tobs
    0.89
    氦
    0.89
     vicinity
    0.86
     endanger
    0.86
    ı
    0.84
    Act Density 0.002%

    No Known Activations