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

    Neuronpedia

    INDEX
    Explanations

    cut short, Jurong Point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fordul
    0.75
    went
    0.72
     llegan
    0.69
     அவ்வ
    0.67
    quinho
    0.67
    )=>
    0.67
    ≿
    0.66
    erenza
    0.66
    ulador
    0.65
    ंनो
    0.65
    POSITIVE LOGITS
    ফিক
    0.71
     Total
    0.70
    Total
    0.68
     link
    0.65
     total
    0.65
     Link
    0.64
     preparation
    0.63
    リンク
    0.63
    total
    0.63
    वटी
    0.63
    Act Density 0.003%

    No Known Activations