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

    Neuronpedia

    INDEX
    Explanations

    programming concepts and logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    级的
    0.44
     practition
    0.43
    級
    0.42
    𝚓
    0.41
    𝚏
    0.40
    ရှင်
    0.40
    すご
    0.39
    可见
    0.39
     ओळख
    0.39
    业协会
    0.38
    POSITIVE LOGITS
    andae
    0.39
     Top
    0.38
     compensation
    0.36
    restrial
    0.36
     Equation
    0.36
     columna
    0.36
     уравнения
    0.36
     equation
    0.35
     कॉलम
    0.35
    mountain
    0.35
    Act Density 0.000%

    No Known Activations