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

    Neuronpedia

    INDEX
    Explanations

    technical and legal concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ترك
    0.93
     अवै
    0.93
    ichen
    0.91
    ate
    0.89
    েশ
    0.88
    ie
    0.87
    Adi
    0.87
    ese
    0.85
    ontan
    0.84
    Invalid
    0.84
    POSITIVE LOGITS
     boasts
    1.06
     glassy
    1.06
     beloved
    1.04
     previous
    1.04
     গিয়াছেন
    1.03
     cables
    1.03
     mga
    1.03
     notched
    1.02
    globalMap
    1.01
     exalted
    1.01
    Act Density 0.001%

    No Known Activations