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
    (dt
    -0.06
     edilm
    -0.06
    Still
    -0.06
     θα
    -0.06
    蜘蛛
    -0.06
     Calvin
    -0.06
     Sem
    -0.06
    Mob
    -0.05
    Restart
    -0.05
    deck
    -0.05
    POSITIVE LOGITS
     "),
    0.07
    yro
    0.07
     bumper
    0.07
    ψει
    0.06
    едь
    0.06
    -Петерб
    0.06
     설
    0.06
    ITION
    0.06
     bodyParser
    0.06
     watershed
    0.06
    Act Density 0.031%

    No Known Activations