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

    Neuronpedia

    INDEX
    Explanations

    I am am

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شوند
    0.90
     বলিয়া
    0.85
     themselves
    0.83
     предполагает
    0.83
    してくれる
    0.83
    tembre
    0.81
    くれます
    0.81
     자기
    0.81
     possano
    0.80
     puissent
    0.79
    POSITIVE LOGITS
     am
    3.88
    Am
    2.58
     Am
    2.58
    am
    2.34
     AM
    2.11
     हूँ
    1.79
     हूं
    1.66
    AM
    1.64
     amm
    1.61
     jestem
    1.59
    Act Density 0.429%

    No Known Activations