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

    Neuronpedia

    INDEX
    Explanations

    control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ылған
    -0.08
    .Authorization
    -0.08
     mains
    -0.08
     bye
    -0.08
    dere
    -0.08
     AZ
    -0.08
     kitchenette
    -0.08
     (;
    -0.07
    Cook
    -0.07
    _ac
    -0.07
    POSITIVE LOGITS
     கன
    0.09
     структур
    0.08
     variety
    0.08
     sac
    0.07
     MRI
    0.07
     item
    0.07
     varieties
    0.07
     scrutiny
    0.07
     inspection
    0.07
     объект
    0.07
    Act Density 0.006%

    No Known Activations