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

    Neuronpedia

    INDEX
    Explanations

    explicit conditions, throttle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HUD
    0.44
    ੁੰ
    0.41
    Lloyd
    0.40
    ुत
    0.39
    ăng
    0.39
    quantum
    0.39
     $+
    0.39
    MyToolkit
    0.39
     urme
    0.39
     sprint
    0.38
    POSITIVE LOGITS
     ready
    0.43
    រូប
    0.41
    접
    0.39
     tennis
    0.38
     Animations
    0.38
    Animations
    0.37
     Dij
    0.37
     Cori
    0.36
     অথ
    0.36
     Koi
    0.36
    Act Density 0.000%

    No Known Activations