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

    Neuronpedia

    INDEX
    Explanations

    exchanges, excitations, hatches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WRITE
    0.48
    NE
    0.46
    SECTION
    0.45
    小数点
    0.45
    นิ
    0.43
    èmes
    0.43
    äd
    0.43
    und
    0.42
    ฑ
    0.42
    ะ
    0.42
    POSITIVE LOGITS
    fptr
    0.51
     caches
    0.46
     interfaces
    0.45
     архівів
    0.45
     voltages
    0.45
     exchanges
    0.44
     expedi
    0.44
     excitations
    0.44
     hatches
    0.44
    кай
    0.43
    Act Density 0.001%

    No Known Activations