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

    Neuronpedia

    INDEX
    Explanations

    webpage content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }`}↵
    -0.06
    گاهی
    -0.06
    busters
    -0.06
     offend
    -0.06
     prac
    -0.06
    dığ
    -0.06
    spo
    -0.06
     })↵↵
    -0.06
     Darling
    -0.06
    Dom
    -0.06
    POSITIVE LOGITS
    рукт
    0.07
     duration
    0.06
     RC
    0.06
     subsequent
    0.06
     communism
    0.06
     diye
    0.06
    adier
    0.06
     GetType
    0.06
    045
    0.06
    (dist
    0.06
    Act Density 0.078%

    No Known Activations