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

    Neuronpedia

    INDEX
    Explanations

    Expectation/speculation prediction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evrop
    -0.07
     disadvantages
    -0.06
    &,
    -0.06
     NA
    -0.06
    اریخ
    -0.06
    .RES
    -0.06
     accountId
    -0.06
     semi
    -0.06
    73
    -0.06
    
    -0.06
    POSITIVE LOGITS
     attract
    0.07
     DRIVE
    0.07
    relations
    0.07
     separ
    0.07
    Castle
    0.06
    结构
    0.06
    ALTER
    0.06
    рик
    0.06
    Along
    0.06
     Exists
    0.06
    Act Density 0.018%

    No Known Activations