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

    Neuronpedia

    INDEX
    Explanations

    elasticity and feasibility calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    َّة
    0.50
     খবর
    0.47
     फेव
    0.47
    ardin
    0.47
     familiare
    0.47
    クタ
    0.46
     信息
    0.46
     環境
    0.44
    ค้า
    0.44
    itaria
    0.43
    POSITIVE LOGITS
     be
    0.49
    Золо
    0.44
     GeForce
    0.42
     bluff
    0.42
    С
    0.42
    ال
    0.42
    on
    0.41
    dır
    0.41
    ifikat
    0.41
    Գ
    0.40
    Act Density 0.003%

    No Known Activations