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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RAR
    -0.07
    +)
    -0.07
     invite
    -0.07
    控制
    -0.07
     IDE
    -0.07
    ・
    -0.06
    VE
    -0.06
    /cl
    -0.06
    /gr
    -0.06
     approved
    -0.06
    POSITIVE LOGITS
     userID
    0.06
    ững
    0.06
    opaque
    0.06
     artillery
    0.06
     numberWith
    0.06
     �
    0.06
    (interface
    0.06
    \Requests
    0.06
     Spark
    0.05
     pä
    0.05
    Act Density 0.352%

    No Known Activations