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

    Neuronpedia

    INDEX
    Explanations

    otherwise, oscilloscope, Rapid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     나오고
    0.43
     rape
    0.42
    yout
    0.42
    ↵↵↵↵↵↵↵↵↵↵↵
    0.40
    ☜
    0.39
    ‏:‏
    0.39
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.38
    ↵↵↵↵↵↵↵↵↵
    0.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.38
     mandarin
    0.38
    POSITIVE LOGITS
     ,
    0.44
    ,
    0.41
     —
    0.40
    ad
    0.38
    .,
    0.37
     –
    0.36
    БУ
    0.35
    (_
    0.35
     অথচ
    0.34
     चुने
    0.34
    Act Density 0.000%

    No Known Activations