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

    Neuronpedia

    INDEX
    Explanations

    Example 1: Input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    十九章
    0.34
    鲳
    0.33
    OLIS
    0.33
    ༩
    0.33
    করিয়া
    0.33
    უტ
    0.32
    crystals
    0.32
    Swe
    0.32
     कर्क
    0.32
    ")%>%
    0.32
    POSITIVE LOGITS
     Constraints
    0.87
    Constraints
    0.86
     constraints
    0.80
    constraints
    0.74
     constraint
    0.71
    Constraint
    0.68
    约束
    0.68
    Input
    0.66
     Input
    0.66
     Constraint
    0.64
    Act Density 0.012%

    No Known Activations