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

    Neuronpedia

    INDEX
    Explanations

    facing challenges or avoiding jargon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bilhões
    0.46
     milhões
    0.45
     ulic
    0.41
     öld
    0.41
     stocks
    0.40
     millions
    0.40
     আজি
    0.40
     billions
    0.40
     Millions
    0.40
     trillions
    0.39
    POSITIVE LOGITS
    whether
    0.42
    する場合
    0.41
     অন্যতম
    0.41
     whether
    0.40
     શું
    0.40
    ond
    0.39
    gather
    0.38
    怎樣
    0.38
     пам
    0.38
     sådan
    0.38
    Act Density 0.000%

    No Known Activations