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

    Neuronpedia

    INDEX
    Explanations

    update function call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    indan
    0.69
     Ko
    0.66
     Сред
    0.65
     motivating
    0.65
    ChooseCharacter
    0.64
    섬
    0.62
     الص
    0.62
    minipage
    0.62
     arisen
    0.61
    চলিত
    0.61
    POSITIVE LOGITS
     filme
    0.73
    गणना
    0.69
     statute
    0.68
    report
    0.68
    സ്റ്റ
    0.68
     イエロー
    0.68
     metter
    0.67
     sò
    0.66
     রিপোর্ট
    0.65
    ポジション
    0.65
    Act Density 0.000%

    No Known Activations