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

    Neuronpedia

    INDEX
    Explanations

    Non-English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kosher
    -0.07
     PRIVATE
    -0.06
    city
    -0.06
     ListTile
    -0.06
    Captain
    -0.06
    zi
    -0.06
    -danger
    -0.06
    หาร
    -0.06
    isspace
    -0.06
     Thomson
    -0.06
    POSITIVE LOGITS
    (nil
    0.09
    UED
    0.07
     konus
    0.07
    以来
    0.07
     tried
    0.07
     effort
    0.07
     garg
    0.07
     GmbH
    0.07
     perce
    0.07
     pokus
    0.07
    Act Density 0.019%

    No Known Activations