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

    Neuronpedia

    INDEX
    Explanations

    code syntax and grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brand
    -0.08
    LOUD
    -0.08
     ladder
    -0.08
     兰
    -0.08
     ladd
    -0.08
     patch
    -0.07
    ്ല
    -0.07
    @@@@@@@@
    -0.07
    品牌
    -0.07
     lal
    -0.07
    POSITIVE LOGITS
     Bedingungen
    0.10
     voorwaarden
    0.10
    조건
    0.10
    .Condition
    0.09
     koş
    0.09
    Conditions
    0.09
    .conditions
    0.09
     Voraussetzungen
    0.09
    conditions
    0.09
     условий
    0.09
    Act Density 0.008%

    No Known Activations