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

    Neuronpedia

    INDEX
    Explanations

    LEGO analogies for explaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    стве
    0.86
    zí
    0.81
    3
    0.80
    ക്ക്
    0.80
     possède
    0.77
    MEX
    0.75
    льзова
    0.74
    ﺼ
    0.73
    થી
    0.72
     Mares
    0.72
    POSITIVE LOGITS
    ร
    0.90
    س
    0.78
    ir
    0.77
    aren
    0.76
    ोरेशन
    0.74
    ory
    0.71
    erto
    0.71
    sa
    0.70
    ุ
    0.70
    ages
    0.69
    Act Density 0.005%

    No Known Activations