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

    Neuronpedia

    INDEX
    Explanations

    the CISO / roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.47
    r
    0.47
    yog
    0.47
    f
    0.46
    editing
    0.45
    র
    0.45
    mars
    0.44
    ifrån
    0.43
     포
    0.42
    in
    0.42
    POSITIVE LOGITS
     wretched
    0.47
    τζ
    0.47
    慮
    0.46
    Кто
    0.43
    ApiModel
    0.43
    щину
    0.43
    Antes
    0.43
     horrid
    0.43
     bruta
    0.42
    штейн
    0.42
    Act Density 0.001%

    No Known Activations