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

    Neuronpedia

    INDEX
    Explanations

    section

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tam
    -0.08
     pur
    -0.07
     وجود
    -0.07
    -door
    -0.07
     Night
    -0.06
     Time
    -0.06
    degree
    -0.06
     renting
    -0.06
     interviews
    -0.06
     night
    -0.06
    POSITIVE LOGITS
     section
    0.15
     Section
    0.10
     sections
    0.09
    .highlight
    0.07
    豪
    0.07
     climax
    0.07
    }()↵↵
    0.07
     Sections
    0.06
    gboolean
    0.06
    ALSE
    0.06
    Act Density 0.012%

    No Known Activations