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

    Neuronpedia

    INDEX
    Explanations

    Message

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cleanup
    -0.07
     fit
    -0.07
     Roof
    -0.07
    4
    -0.07
    II
    -0.07
    全
    -0.07
     wild
    -0.06
     Built
    -0.06
     Friedrich
    -0.06
    统
    -0.06
    POSITIVE LOGITS
    Message
    0.17
     message
    0.14
     Message
    0.14
    message
    0.14
     messages
    0.12
    	message
    0.12
     setMessage
    0.12
    (message
    0.11
     MSG
    0.11
    MessageType
    0.11
    Act Density 0.038%

    No Known Activations