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

    Neuronpedia

    INDEX
    Explanations

    disabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sparks
    -0.07
    flate
    -0.07
     propaganda
    -0.07
    STM
    -0.06
     BOX
    -0.06
     фото
    -0.06
     bubbles
    -0.06
    产业
    -0.06
    申请
    -0.06
     deadline
    -0.06
    POSITIVE LOGITS
    <?>
    0.07
    uele
    0.07
     mdb
    0.07
     brilliantly
    0.07
    -unused
    0.06
    ُل
    0.06
    volution
    0.06
     gboolean
    0.06
     egret
    0.06
     Unsure
    0.06
    Act Density 0.032%

    No Known Activations