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

    Neuronpedia

    INDEX
    Explanations

    X11 programming

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ptr
    0.75
     monitor
    0.74
     slate
    0.73
     presa
    0.70
     arsen
    0.70
    த்தார்
    0.69
     ওভারে
    0.69
     धान
    0.69
     smartwatch
    0.69
    zaXRvcn
    0.68
    POSITIVE LOGITS
    olev
    0.65
     निवास
    0.64
    र्नर
    0.63
    াবির
    0.60
     instancia
    0.60
     കരു
    0.60
    ุล
    0.59
    ंजन
    0.59
    ത്വ
    0.59
     अंग्रेज
    0.58
    Act Density 0.003%

    No Known Activations