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

    Neuronpedia

    INDEX
    Explanations

    domain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EDT
    -0.06
     Boston
    -0.06
     이후
    -0.06
    (labels
    -0.06
    .ch
    -0.06
    .chapter
    -0.06
     populated
    -0.06
    Rare
    -0.06
     tsp
    -0.06
    izzle
    -0.06
    POSITIVE LOGITS
    domain
    0.07
    ho
    0.07
    adium
    0.07
    _MA
    0.06
    hub
    0.06
     Missing
    0.06
     PARA
    0.06
     Automated
    0.06
    �u
    0.06
    ormal
    0.06
    Act Density 0.002%

    No Known Activations