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

    Neuronpedia

    INDEX
    Explanations

    event then point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mathrm
    0.54
     as
    0.46
    <0xE3>
    0.45
     Bulldog
    0.45
    0.45
     Um
    0.45
     Technician
    0.45
     water
    0.45
     chalk
    0.44
     Cary
    0.44
    POSITIVE LOGITS
     রহিম
    0.52
     하게
    0.50
     առ
    0.49
    🗨
    0.49
     показывает
    0.49
    naires
    0.48
    minsize
    0.48
    getStartState
    0.48
    ዚ
    0.48
    нос
    0.47
    Act Density 0.000%

    No Known Activations