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

    Neuronpedia

    INDEX
    Explanations

    ER

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compensation
    -0.07
    agento
    -0.06
    slots
    -0.06
     guilt
    -0.06
    OND
    -0.06
     housing
    -0.06
    avadoc
    -0.06
    assistant
    -0.06
    psz
    -0.06
    .Notification
    -0.06
    POSITIVE LOGITS
     vibr
    0.07
    /img
    0.07
    ыс
    0.07
     War
    0.06
     Ceremony
    0.06
     vibrant
    0.06
    勇
    0.06
     src
    0.06
     bulundu
    0.06
     běž
    0.06
    Act Density 0.001%

    No Known Activations