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

    Neuronpedia

    INDEX
    Explanations

    spine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arges
    -0.07
    ocs
    -0.07
    레스
    -0.06
    όδ
    -0.06
    IClient
    -0.06
    .Pixel
    -0.06
    amples
    -0.06
    jections
    -0.06
    ağ
    -0.06
    iotic
    -0.06
    POSITIVE LOGITS
     spine
    0.09
     watchdog
    0.07
     диви
    0.07
     repair
    0.07
     Aspen
    0.06
     Repair
    0.06
     DONE
    0.06
     firefighters
    0.06
    ‐‐
    0.06
     Chili
    0.06
    Act Density 0.001%

    No Known Activations