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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ｌ
    -0.07
    VIP
    -0.07
     shaping
    -0.07
     MX
    -0.07
    .entrySet
    -0.06
    ARSER
    -0.06
    (IM
    -0.06
    арамет
    -0.06
    ฤษภาคม
    -0.06
    ammen
    -0.06
    POSITIVE LOGITS
     crews
    0.07
     Responsible
    0.06
    .resp
    0.06
     indicators
    0.06
    ...)↵
    0.06
    DELAY
    0.06
    (datas
    0.06
    .Lerp
    0.06
    ueue
    0.06
     теб
    0.06
    Act Density 0.013%

    No Known Activations