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

    Neuronpedia

    INDEX
    Explanations

    library installation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mínimo
    1.34
     Actualmente
    1.28
    daki
    1.25
    servlet
    1.24
     dugo
    1.24
     logró
    1.23
     Schritte
    1.23
    自分
    1.23
     făcut
    1.22
    kath
    1.22
    POSITIVE LOGITS
    ১
    1.47
    ট
    1.37
    с
    1.24
    \|
    1.21
    ان
    1.18
    б
    1.17
    i
    1.05
    mqtt
    1.04
    }[!
    1.02
    ====
    1.02
    Act Density 0.001%

    No Known Activations