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

    Neuronpedia

    INDEX
    Explanations

    family relationships and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Durante
    1.37
    ן
    1.30
    [
    1.29
    י
    1.24
    ры
    1.20
    ે
    1.17
    ﹞
    1.16
     poignant
    1.15
    ות
    1.13
    Dieses
    1.13
    POSITIVE LOGITS
    r
    1.77
    le
    1.58
    ra
    1.57
    en
    1.50
    og
    1.50
    ok
    1.50
    nd
    1.47
    j
    1.47
    ug
    1.44
    äne
    1.43
    Act Density 0.001%

    No Known Activations