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

    Neuronpedia

    INDEX
    Explanations

    CVE, NAS, macOS, seedlings, business plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iseerd
    0.82
    ıkları
    0.76
     ver
    0.74
     sơ
    0.72
     mata
    0.71
    ジュ
    0.70
     præ
    0.69
    ゼ
    0.69
    asi
    0.69
    の見
    0.69
    POSITIVE LOGITS
    7
    2.08
    6
    1.94
    8
    1.93
    9
    1.85
    4
    1.79
    3
    1.77
    5
    1.75
    0
    1.62
    煖
    1.50
     combust
    1.49
    Act Density 0.126%

    No Known Activations