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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    699
    -0.07
     quỹ
    -0.07
     Those
    -0.07
    ดย
    -0.07
     �
    -0.06
    かに
    -0.06
     ellos
    -0.06
     示
    -0.06
     verileri
    -0.06
     ADMIN
    -0.06
    POSITIVE LOGITS
    ming
    0.07
    _boost
    0.06
    orno
    0.06
     Lock
    0.06
    ampler
    0.06
    ‌پدی
    0.06
     experimenting
    0.06
    wort
    0.06
     errorCallback
    0.06
     lem
    0.06
    Act Density 0.070%

    No Known Activations