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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Karel
    -0.08
     Honest
    -0.07
     학교
    -0.06
    =nil
    -0.06
     our
    -0.06
     startled
    -0.06
     Pharmac
    -0.06
     Poe
    -0.06
     TP
    -0.06
    俺は
    -0.06
    POSITIVE LOGITS
    輔
    0.07
    โล
    0.07
     技
    0.07
    cherche
    0.07
    (separator
    0.06
     cable
    0.06
     hoping
    0.06
     patio
    0.06
    ोच
    0.06
    _LR
    0.06
    Act Density 0.012%

    No Known Activations