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

    Neuronpedia

    INDEX
    Explanations

    cover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    олько
    -0.07
    pliant
    -0.07
    obby
    -0.06
    ATEGY
    -0.06
     liệt
    -0.06
    .onNext
    -0.06
    ope
    -0.06
    metic
    -0.06
    coffee
    -0.06
    Uuid
    -0.06
    POSITIVE LOGITS
    丁
    0.06
     dances
    0.06
     //~
    0.06
     snaps
    0.06
     прос
    0.06
     Rebel
    0.06
     |--------------------------------------------------------------------------↵
    0.06
    	CG
    0.06
     Minuten
    0.06
     ترجمه
    0.06
    Act Density 0.015%

    No Known Activations