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

    Neuronpedia

    INDEX
    Explanations

    recommend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	intent
    -0.08
    /payment
    -0.07
     prise
    -0.06
     proverb
    -0.06
    fter
    -0.06
    otton
    -0.06
     développ
    -0.06
    _checksum
    -0.06
     survive
    -0.06
     Commander
    -0.06
    POSITIVE LOGITS
     arbit
    0.07
     lacked
    0.06
    üt
    0.06
    还是
    0.06
    ugging
    0.06
    ,Th
    0.06
    391
    0.06
    ÖL
    0.06
    UniqueId
    0.06
    赞
    0.06
    Act Density 0.018%

    No Known Activations