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

    Neuronpedia

    INDEX
    Explanations

    experimental injections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -proof
    -0.07
     frozen
    -0.07
    VES
    -0.06
     привы
    -0.06
     dividends
    -0.06
     lib
    -0.06
    �
    -0.06
    MD
    -0.06
     appeal
    -0.06
     kinds
    -0.06
    POSITIVE LOGITS
    (fb
    0.07
    Но
    0.06
     لذا
    0.06
     çab
    0.06
     dan
    0.06
    	il
    0.06
     perpetrated
    0.06
    igrationBuilder
    0.06
    .Dock
    0.06
     FactoryGirl
    0.06
    Act Density 0.029%

    No Known Activations