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

    Neuronpedia

    INDEX
    Explanations

    establishing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nationwide
    -0.07
     Sử
    -0.07
     طبیعی
    -0.07
    ias
    -0.06
     Nordic
    -0.06
    쿠
    -0.06
     Yuri
    -0.06
    antd
    -0.06
    iei
    -0.06
     furnish
    -0.06
    POSITIVE LOGITS
    	unsigned
    0.07
     sujet
    0.07
    tbl
    0.06
    ....↵↵
    0.06
     jedno
    0.06
     звіт
    0.06
    speech
    0.06
    Selectors
    0.06
     lange
    0.06
    connecting
    0.06
    Act Density 0.001%

    No Known Activations