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

    Neuronpedia

    INDEX
    Explanations

    reducer or reduce function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সাংস
    0.42
     kript
    0.41
    ゼ
    0.39
    撮影
    0.39
     Christoph
    0.38
     سرب
    0.37
    হা
    0.37
    Juni
    0.36
     needing
    0.36
     Biological
    0.36
    POSITIVE LOGITS
    Reducer
    1.09
     reducer
    1.09
    reducer
    1.05
     redu
    0.95
    reducers
    0.94
     initialState
    0.89
    reduce
    0.87
    Reduce
    0.83
    Reducing
    0.81
     Reduction
    0.80
    Act Density 0.007%

    No Known Activations