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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    áo
    -0.07
    ght
    -0.06
     Kills
    -0.06
     education
    -0.06
    olit
    -0.06
    “I
    -0.06
     gec
    -0.06
    	object
    -0.06
    .checked
    -0.06
     increases
    -0.06
    POSITIVE LOGITS
     Gilles
    0.07
     Francois
    0.07
    .Marshal
    0.07
    units
    0.07
    EventManager
    0.06
     polls
    0.06
    gement
    0.06
     Interpret
    0.06
    Venue
    0.06
     Malcolm
    0.06
    Act Density 0.106%

    No Known Activations