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

    Neuronpedia

    INDEX
    Explanations

    aid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     repost
    -0.07
    شمل
    -0.07
     WEIGHT
    -0.07
    ϓ
    -0.07
    變
    -0.07
    -role
    -0.07
    毫克
    -0.07
    gender
    -0.07
    ча
    -0.07
    沨
    -0.07
    POSITIVE LOGITS
     hackers
    0.07
    どこ
    0.07
    eceği
    0.06
     Louise
    0.06
    Talking
    0.06
    お話
    0.06
     dps
    0.06
    akes
    0.06
    diğiniz
    0.06
    侦探
    0.06
    Act Density 0.001%

    No Known Activations