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

    Neuronpedia

    INDEX
    Explanations

    extension, continuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     migraines
    -0.08
    Ign
    -0.08
    -loving
    -0.07
    $json
    -0.07
     mba
    -0.07
    408
    -0.07
     ki
    -0.07
     čist
    -0.07
    :")↵
    -0.07
    有关
    -0.07
    POSITIVE LOGITS
     continuation
    0.11
     continuidade
    0.10
     continuidad
    0.09
    Continuation
    0.09
     continuity
    0.09
    threads
    0.09
     threads
    0.09
     이어
    0.09
     folgt
    0.09
     Threads
    0.08
    Act Density 0.016%

    No Known Activations