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

    Neuronpedia

    INDEX
    Explanations

    Organized activities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     terrible
    -0.07
    ihu
    -0.06
     потер
    -0.06
     isLoading
    -0.06
    _INVALID
    -0.06
    وله
    -0.06
    -change
    -0.06
     Accounting
    -0.06
    spin
    -0.06
    semblies
    -0.06
    POSITIVE LOGITS
     вариан
    0.06
    (HttpContext
    0.06
    _AB
    0.06
    ��
    0.06
    すれば
    0.05
    throp
    0.05
     Ком
    0.05
    quets
    0.05
     आव
    0.05
    می
    0.05
    Act Density 0.051%

    No Known Activations