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

    Neuronpedia

    INDEX
    Explanations

    options and suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Can
    0.45
    灿
    0.45
     בי
    0.45
     Eph
    0.45
    vt
    0.44
    up
    0.44
     आणि
    0.44
    약
    0.44
    oran
    0.44
    ică
    0.43
    POSITIVE LOGITS
     centroids
    0.52
     programmes
    0.49
     multinationals
    0.47
     Programmes
    0.46
     vaccinate
    0.46
     resettlement
    0.45
    olisme
    0.45
     rotate
    0.44
     redistribute
    0.44
     condense
    0.44
    Act Density 0.006%

    No Known Activations