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

    Neuronpedia

    INDEX
    Explanations

    idle and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fusible
    0.39
     Alber
    0.38
    ับสน
    0.37
    活用
    0.37
    askar
    0.37
     Pres
    0.37
     Sy
    0.36
     Hyd
    0.36
     Albanese
    0.36
    প্রেস
    0.36
    POSITIVE LOGITS
    wild
    0.41
    wheel
    0.40
     gou
    0.39
    bio
    0.39
    璋
    0.39
    factory
    0.39
    hando
    0.38
    LIB
    0.38
    jší
    0.38
     城
    0.38
    Act Density 0.027%

    No Known Activations