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

    Neuronpedia

    INDEX
    Explanations

    accessibility and ease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    슨
    0.52
    يل
    0.50
     사용하는
    0.49
     연구
    0.48
     จ
    0.47
     ди
    0.46
     actuales
    0.46
     광고
    0.46
     ต
    0.45
     penelitian
    0.45
    POSITIVE LOGITS
    startsWith
    0.46
     Transplantation
    0.46
     Planned
    0.44
    はじめ
    0.43
    e
    0.43
     Goes
    0.42
     Ortiz
    0.42
    Supports
    0.42
    רץ
    0.42
     leftover
    0.41
    Act Density 0.000%

    No Known Activations