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

    Neuronpedia

    INDEX
    Explanations

    race to the bottom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HIDE
    0.58
    Papa
    0.54
    WriteStream
    0.52
     economic
    0.51
    econom
    0.50
    H
    0.50
     Miocene
    0.50
    G
    0.50
    anyahu
    0.49
     popOperand
    0.49
    POSITIVE LOGITS
    ты
    0.55
     poucos
    0.52
    ي
    0.51
     bekannten
    0.48
    د
    0.47
    َف
    0.46
    ナ
    0.46
     K
    0.46
    ла
    0.46
    тності
    0.45
    Act Density 0.000%

    No Known Activations