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

    Neuronpedia

    INDEX
    Explanations

    approved for use or by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    1.49
    在
    0.88
    a
    0.87
     في
    0.86
     inorder
    0.80
    ।
    0.78
    d
    0.77
     Abgerufen
    0.77
    Ο
    0.76
    ย
    0.75
    POSITIVE LOGITS
    л
    0.89
    ية
    0.89
    ता
    0.86
    ленных
    0.83
    них
    0.80
    ária
    0.79
    лера
    0.79
    ay
    0.77
    ل
    0.75
    τας
    0.74
    Act Density 0.002%

    No Known Activations