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

    Neuronpedia

    INDEX
    Explanations

    code/data files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     والإ
    -0.06
    ิดต
    -0.06
    	expect
    -0.06
    소개
    -0.06
    ̈
    -0.06
    (IP
    -0.06
    setItem
    -0.06
     nasıl
    -0.06
    uckets
    -0.06
    lerle
    -0.06
    POSITIVE LOGITS
     implicitly
    0.07
    бут
    0.07
    rians
    0.06
    Diagnostic
    0.06
    ownik
    0.06
    ovsky
    0.06
    author
    0.06
     maç
    0.06
    ols
    0.06
     seasonal
    0.06
    Act Density 0.001%

    No Known Activations