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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ')</
    -0.07
    orses
    -0.07
     coordinates
    -0.07
    IF
    -0.07
     Aggregate
    -0.07
    iment
    -0.06
     fight
    -0.06
    F
    -0.06
     Affiliate
    -0.06
    ognition
    -0.06
    POSITIVE LOGITS
    /tinyos
    0.06
     kraj
    0.06
    zipcode
    0.06
    มหาว
    0.06
    краї
    0.06
    ナー
    0.06
     XHTML
    0.05
     århus
    0.05
     yeniden
    0.05
     FOUND
    0.05
    Act Density 0.011%

    No Known Activations