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

    Neuronpedia

    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     address
    -0.63
     command
    -0.62
     account
    -0.54
     last
    -0.52
     IP
    -0.50
     start
    -0.49
     do
    -0.46
     stable
    -0.46
     fill
    -0.46
     make
    -0.45
    POSITIVE LOGITS
    featureID
    0.98
     defaultstate
    0.89
    ValueStyle
    0.86
     Normdatei
    0.84
     חיצוניים
    0.81
    parsedMessage
    0.79
    afficheront
    0.79
    InjectAttribute
    0.77
     surla
    0.76
     <<<<<<<<<<<<<<
    0.76
    Act Density 0.009%

    No Known Activations