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

    Neuronpedia

    INDEX
    Explanations

    thanks for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ī
    0.44
    ders
    0.41
    ded
    0.41
    dimension
    0.40
     municipality
    0.39
     triumph
    0.38
    ointed
    0.38
    deling
    0.38
    clesiastical
    0.38
    depart
    0.37
    POSITIVE LOGITS
    栲
    0.43
     ਸਿੰ
    0.43
     보도록
    0.42
    睪
    0.42
     беремен
    0.42
     calific
    0.40
     постро
    0.40
     கொடுத்து
    0.40
     борь
    0.39
     TESTING
    0.39
    Act Density 0.001%

    No Known Activations