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

    Neuronpedia

    INDEX
    Explanations

    assembly line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     synthes
    1.11
    ль
    0.98
    .
    0.98
     legitim
    0.98
    ]
    0.90
     reorgan
    0.86
     in
    0.84
    ch
    0.83
    我
    0.81
     sanit
    0.80
    POSITIVE LOGITS
    ן
    1.20
     assembly
    1.17
     Assembly
    1.16
    ro
    1.02
    ת
    1.00
    ল
    1.00
    트
    0.98
     assemblies
    0.96
    ರ
    0.95
     ASSEMBLY
    0.95
    Act Density 0.004%

    No Known Activations