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

    Neuronpedia

    INDEX
    Explanations

    trying to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.52
    ...]
    0.47
     &
    0.46
    </h3>
    0.45
     therapies
    0.44
    scapes
    0.43
     e
    0.43
     yoga
    0.43
     digestive
    0.43
    !”
    0.43
    POSITIVE LOGITS
    أ
    0.59
    żenia
    0.55
    バイト
    0.54
    áře
    0.54
    était
    0.53
     quiso
    0.53
     jaoks
    0.52
     sétimo
    0.52
    ক্সি
    0.52
    उदाहरण
    0.52
    Act Density 1.862%

    No Known Activations