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

    Neuronpedia

    INDEX
    Explanations

    Delaware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Industry
    -0.07
     Yus
    -0.07
     April
    -0.07
     sun
    -0.07
     Icons
    -0.07
     Jugend
    -0.07
     mountains
    -0.07
     ego
    -0.07
    /cpu
    -0.07
     Accident
    -0.06
    POSITIVE LOGITS
     Delaware
    0.16
     Newark
    0.07
     розрахун
    0.07
    ウェ
    0.07
     뭐
    0.07
    uppe
    0.07
     замов
    0.07
    oplevel
    0.07
    -A
    0.07
     <+
    0.06
    Act Density 0.001%

    No Known Activations