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

    Neuronpedia

    INDEX
    Explanations

    links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overwrite
    -0.07
    チュ
    -0.07
     declarations
    -0.06
    _again
    -0.06
    ียร
    -0.06
    表情
    -0.06
    	names
    -0.06
    령
    -0.06
     незалеж
    -0.06
     owe
    -0.06
    POSITIVE LOGITS
     Wilmington
    0.07
    Lifecycle
    0.07
    normalized
    0.06
    Trim
    0.06
     vielleicht
    0.06
     Aircraft
    0.06
     hemorrh
    0.06
    -marker
    0.06
     JS
    0.06
    ymoon
    0.06
    Act Density 0.004%

    No Known Activations