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

    Neuronpedia

    INDEX
    Explanations

    playing games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.05
    nier
    0.90
    一声
    0.85
    urion
    0.84
    nings
    0.82
    ような
    0.81
    aneous
    0.80
    nable
    0.80
     titan
    0.78
    ering
    0.77
    POSITIVE LOGITS
    '
    1.11
    та
    0.91
    ים
    0.91
    HttpRequest
    0.91
     informatique
    0.88
     arrête
    0.86
     управления
    0.86
    д
    0.86
    ஸ்
    0.85
     разговари
    0.85
    Act Density 0.085%

    No Known Activations