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

    Neuronpedia

    INDEX
    Explanations

    US departments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    इस
    -0.07
     lado
    -0.07
     từng
    -0.06
    角色
    -0.06
    Ban
    -0.06
     limit
    -0.06
    klady
    -0.06
    Pref
    -0.06
     Král
    -0.06
    いう
    -0.06
    POSITIVE LOGITS
     меди
    0.06
     RAF
    0.06
     scouting
    0.06
    َق
    0.06
     DRAW
    0.06
    elog
    0.06
    loggedIn
    0.06
    ılığ
    0.06
    摇
    0.06
    statement
    0.06
    Act Density 0.025%

    No Known Activations