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

    Neuronpedia

    INDEX
    Explanations

    code repositories and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     製造
    0.55
     Gegensatz
    0.54
    rante
    0.54
     químicos
    0.54
     Microscopy
    0.53
     MCSF
    0.52
     joueurs
    0.51
     কাহারও
    0.51
     مخالف
    0.50
    ORDAN
    0.49
    POSITIVE LOGITS
    their
    0.57
     their
    0.56
    0.55
    the
    0.54
    ↵
    0.52
    core
    0.49
     the
    0.47
    test
    0.45
    training
    0.45
    service
    0.43
    Act Density 0.000%

    No Known Activations