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

    Neuronpedia

    INDEX
    Explanations

    probability

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     siquiera
    0.38
     serem
    0.38
    に見
    0.37
     auxquelles
    0.36
     Jangan
    0.36
     Lately
    0.36
     รู้
    0.35
     हैज
    0.35
    ">[
    0.35
     kanssa
    0.35
    POSITIVE LOGITS
     likely
    1.65
    likely
    1.38
     probably
    1.26
     Likely
    1.23
     undoubtedly
    1.13
     provavelmente
    1.10
     probablemente
    1.07
     probabilmente
    1.07
     probablement
    1.05
    probably
    1.02
    Act Density 0.589%

    No Known Activations