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

    Neuronpedia

    INDEX
    Explanations

    Names/Introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ok
    -0.07
     wandering
    -0.07
     Μον
    -0.06
    _dict
    -0.06
    ेल
    -0.06
    집
    -0.06
    ��
    -0.06
     forefront
    -0.06
    kle
    -0.06
     فريق
    -0.06
    POSITIVE LOGITS
     adına
    0.08
     feared
    0.07
    dater
    0.07
    .confirm
    0.07
     zejména
    0.07
    .LabelControl
    0.07
     KeyboardInterrupt
    0.07
     příležit
    0.06
     sondern
    0.06
    _flow
    0.06
    Act Density 0.023%

    No Known Activations