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

    Neuronpedia

    INDEX
    Explanations

    complexType, extends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     med
    -0.08
    stri
    -0.08
     piercing
    -0.07
    mdb
    -0.07
    art
    -0.07
    �
    -0.07
    聚集
    -0.07
     SCP
    -0.07
    est
    -0.07
    �
    -0.06
    POSITIVE LOGITS
    _container
    0.08
    Loss
    0.08
    Salary
    0.07
    nickname
    0.07
    socket
    0.07
    ﳣ
    0.07
    Conn
    0.07
     oczywiście
    0.07
    -blocking
    0.07
    Bridge
    0.07
    Act Density 0.000%

    No Known Activations