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

    Neuronpedia

    INDEX
    Explanations

    code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jis
    -0.08
    ¥
    -0.07
    396
    -0.06
     لإ
    -0.06
    tee
    -0.06
     ISBN
    -0.06
    시오
    -0.06
    jf
    -0.06
    $category
    -0.06
     heb
    -0.06
    POSITIVE LOGITS
     Орг
    0.07
     expenditures
    0.07
    ">'+↵
    0.06
    .tw
    0.06
    ывают
    0.06
    >').
    0.06
     discretionary
    0.06
    	UP
    0.06
     Hilton
    0.06
    Feedback
    0.06
    Act Density 0.000%

    No Known Activations