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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elas
    -0.08
    anian
    -0.07
    Expert
    -0.07
    eceğiz
    -0.07
    香港
    -0.06
    otas
    -0.06
     sciences
    -0.06
    ząd
    -0.06
    ekim
    -0.06
    ctl
    -0.06
    POSITIVE LOGITS
     UFO
    0.07
     mundane
    0.07
     Connector
    0.06
     деп
    0.06
     inher
    0.06
    itmap
    0.06
     Outreach
    0.06
     caravan
    0.05
    <Service
    0.05
     зат
    0.05
    Act Density 0.009%

    No Known Activations