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

    Neuronpedia

    INDEX
    Explanations

    business operating performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gods
    0.86
     AVL
    0.79
     Yes
    0.78
     V
    0.77
     Columns
    0.77
     K
    0.76
     Savage
    0.76
     gods
    0.76
     powerful
    0.75
     Spray
    0.73
    POSITIVE LOGITS
    rically
    1.04
    ب
    0.96
    𝘩
    0.96
    sächlich
    0.95
    uisce
    0.91
    𝑠
    0.91
    sides
    0.90
    اردوش
    0.90
    electrical
    0.89
    ς
    0.89
    Act Density 0.000%

    No Known Activations