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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Calculation
    -0.07
    INST
    -0.06
    üz
    -0.06
    -live
    -0.06
    ictures
    -0.06
     seq
    -0.06
    PERSON
    -0.06
     �
    -0.06
    Offer
    -0.06
     illicit
    -0.06
    POSITIVE LOGITS
    Carthy
    0.07
    _ENTER
    0.07
     مجلس
    0.06
     zdravot
    0.06
    			↵↵
    0.06
     Ron
    0.06
     corporations
    0.06
     Bacon
    0.06
     bé
    0.06
    _IList
    0.06
    Act Density 0.028%

    No Known Activations