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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alesce
    -0.07
    ackage
    -0.07
    ifu
    -0.06
    しく
    -0.06
    哪里
    -0.06
    Suc
    -0.06
    วย
    -0.06
     setter
    -0.06
    妻
    -0.06
    Numbers
    -0.06
    POSITIVE LOGITS
     yaygın
    0.07
    �
    0.07
     důsled
    0.07
    Am
    0.07
     miglior
    0.06
    _USART
    0.06
    ARE
    0.06
    .charAt
    0.06
    ‐
    0.06
     Universal
    0.06
    Act Density 0.021%

    No Known Activations