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

    Neuronpedia

    INDEX
    Explanations

    clothing or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     catheters
    0.40
     배치
    0.40
    িস্থ
    0.39
     kaps
    0.39
     configuring
    0.37
    日々
    0.37
    ﺿ
    0.37
    Christopher
    0.36
     ದೇಹ
    0.36
     peserta
    0.36
    POSITIVE LOGITS
     Without
    0.45
     Avoid
    0.44
     عندنا
    0.44
     తెలుగు
    0.43
     libri
    0.40
     avoid
    0.40
     Our
    0.39
    🏡
    0.38
    lady
    0.38
     அடி
    0.38
    Act Density 0.001%

    No Known Activations