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

    Neuronpedia

    INDEX
    Explanations

    engagement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quoting
    -0.07
    .special
    -0.07
    twenty
    -0.07
    Paul
    -0.07
    17
    -0.07
    18
    -0.07
    rost
    -0.07
    _array
    -0.06
     ((
    -0.06
     priests
    -0.06
    POSITIVE LOGITS
     engage
    0.11
     engaging
    0.11
     engaged
    0.10
     engagement
    0.10
     Engagement
    0.09
     Eng
    0.09
    -eng
    0.08
    Eng
    0.08
    eng
    0.08
     Ferguson
    0.07
    Act Density 0.019%

    No Known Activations