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

    Neuronpedia

    INDEX
    Explanations

    markdown formatted explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ALK
    0.47
    หรือ
    0.47
     เป็น
    0.45
    Known
    0.45
    Leer
    0.45
    jelder
    0.45
     잡
    0.44
    èmes
    0.44
     bertujuan
    0.44
    原创
    0.43
    POSITIVE LOGITS
     clearly
    0.48
     demuestra
    0.48
     claramente
    0.46
    clearly
    0.46
     plot
    0.45
     demonstra
    0.44
     rõ
    0.43
     tyd
    0.43
     visualise
    0.43
     jelas
    0.42
    Act Density 0.060%

    No Known Activations