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

    Neuronpedia

    INDEX
    Explanations

    recognized/known

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consid
    -0.08
    126
    -0.07
    Cel
    -0.07
    cbd
    -0.07
    غن
    -0.06
     적
    -0.06
    enu
    -0.06
     risking
    -0.06
    回答
    -0.06
     ingr
    -0.06
    POSITIVE LOGITS
    ดย
    0.07
    ;">
    0.06
    ी।
    0.06
     "");
↵
    0.06
     �
    0.06
     його
    0.06
    ันยายน
    0.06
     resetting
    0.06
    \Notifications
    0.06
     її
    0.06
    Act Density 0.044%

    No Known Activations