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

    Neuronpedia

    INDEX
    Explanations

    portability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﾞﾞ
    -0.07
    eated
    -0.06
     sentiment
    -0.06
    ��
    -0.06
    緊
    -0.06
     parenting
    -0.06
    자가
    -0.06
    говор
    -0.06
     appetite
    -0.06
     diced
    -0.06
    POSITIVE LOGITS
    Property
    0.07
     DISABLE
    0.07
     능
    0.06
     ipAddress
    0.06
    _ra
    0.06
     fulfilling
    0.06
    _SK
    0.06
    _RES
    0.06
    _boost
    0.06
    _hierarchy
    0.06
    Act Density 0.024%

    No Known Activations