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

    Neuronpedia

    INDEX
    Explanations

    places, events, and specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     with
    0.51
    ِ
    0.50
    with
    0.50
    ी
    0.50
    ُ
    0.49
    You
    0.47
    п
    0.47
    not
    0.45
    of
    0.44
    visit
    0.44
    POSITIVE LOGITS
     kleines
    0.49
     erzählt
    0.48
     gleiche
    0.48
     Scienze
    0.45
    ",[
    0.45
    ependence
    0.45
     ritorno
    0.44
    kuje
    0.44
    fähigkeit
    0.44
    Healthcare
    0.44
    Act Density 0.006%

    No Known Activations