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

    Neuronpedia

    INDEX
    Explanations

    shop floor assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     judicious
    0.97
     IMHO
    0.90
    のでしょう
    0.89
    ですから
    0.89
    .>
    0.87
     exhort
    0.86
     “…
    0.83
     conspicuously
    0.82
     zcela
    0.82
     materially
    0.82
    POSITIVE LOGITS
    됬
    1.19
     বাহিরে
    1.17
     aswell
    1.14
     namelijk
    1.07
     tbh
    1.05
     Doncaster
    1.01
     photoshoot
    0.99
     данный
    0.97
     देखील
    0.96
     downfall
    0.96
    Act Density 0.002%

    No Known Activations