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

    Neuronpedia

    INDEX
    Explanations

    wide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    πτυ
    -0.07
    Retrieve
    -0.07
     NSDictionary
    -0.07
    ７
    -0.06
     posY
    -0.06
     Σε
    -0.06
    NSUInteger
    -0.06
     особлив
    -0.06
    ContentType
    -0.06
     collectionView
    -0.06
    POSITIVE LOGITS
    cj
    0.07
     Jacket
    0.07
    sein
    0.06
    flows
    0.06
     bundles
    0.06
    .Safe
    0.06
    상
    0.06
     Muss
    0.06
     Conte
    0.06
    "os
    0.06
    Act Density 0.016%

    No Known Activations