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

    Neuronpedia

    INDEX
    Explanations

    metal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Liver
    -0.07
    .Observer
    -0.07
     связи
    -0.07
    跋
    -0.07
    洎
    -0.07
    'ai
    -0.07
     suis
    -0.06
    categories
    -0.06
     Etsy
    -0.06
    ("//*[@
    -0.06
    POSITIVE LOGITS
     הילד
    0.07
     shorthand
    0.07
    ｯ
    0.07
     жел
    0.07
     freder
    0.07
    셴
    0.06
     integr
    0.06
    Leading
    0.06
    ffer
    0.06
     delegates
    0.06
    Act Density 0.173%

    No Known Activations