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

    Neuronpedia

    INDEX
    Explanations

    meaning and analogies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jaja
    0.43
    いくつか
    0.43
    υγ
    0.42
     ingat
    0.40
    风险
    0.39
     prochain
    0.39
     véhicules
    0.39
    を楽し
    0.38
     ቤ
    0.38
     rare
    0.38
    POSITIVE LOGITS
    in
    0.47
    ele
    0.44
     Depression
    0.44
     Complaint
    0.44
    with
    0.43
    le
    0.42
    arf
    0.42
    amide
    0.41
    isering
    0.41
    arik
    0.41
    Act Density 0.000%

    No Known Activations