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

    Neuronpedia

    INDEX
    Explanations

    books and publishing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INAL
    -0.07
     statutes
    -0.07
     paved
    -0.06
    isque
    -0.06
    DI
    -0.06
    ор
    -0.06
    เดอร
    -0.06
     upgraded
    -0.06
     Leigh
    -0.06
    	update
    -0.06
    POSITIVE LOGITS
     jejím
    0.07
     varlık
    0.06
    turtle
    0.06
    
    0.06
     desperation
    0.06
    .Free
    0.06
    .Title
    0.06
    、マ
    0.06
    (internal
    0.06
    jeta
    0.06
    Act Density 0.016%

    No Known Activations