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

    Neuronpedia

    INDEX
    Explanations

    Action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ’
    -0.07
    回升
    -0.07
    ))->
    -0.07
     cljs
    -0.06
    OLUME
    -0.06
     injecting
    -0.06
     Coral
    -0.06
    Consult
    -0.06
    /run
    -0.06
     béné
    -0.06
    POSITIVE LOGITS
     ostat
    0.07
    ================
    0.07
    邮政
    0.07
     StringType
    0.07
     desktop
    0.07
    errals
    0.07
    Leap
    0.07
    ','');↵
    0.06
    ماذا
    0.06
     обычно
    0.06
    Act Density 0.001%

    No Known Activations