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

    Neuronpedia

    INDEX
    Explanations

    succession / replacement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orer
    -0.06
     Theater
    -0.06
     twelve
    -0.06
    モン
    -0.06
     appl
    -0.06
     Resident
    -0.06
     mortality
    -0.06
     fourteen
    -0.06
     hostile
    -0.06
     Suffolk
    -0.06
    POSITIVE LOGITS
    .emit
    0.07
    (posts
    0.06
     fitting
    0.06
     (?,
    0.06
     (/
    0.06
    (Tag
    0.06
    (bits
    0.06
     Dirt
    0.06
    doctype
    0.06
    tag
    0.06
    Act Density 0.010%

    No Known Activations