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

    Neuronpedia

    INDEX
    Explanations

    American

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getto
    -0.06
    ERC
    -0.06
    (startDate
    -0.06
    ैज
    -0.06
    .windows
    -0.06
    .ge
    -0.06
     Ian
    -0.06
    .Contract
    -0.06
    项目
    -0.05
    CEE
    -0.05
    POSITIVE LOGITS
     weaknesses
    0.07
     Destructor
    0.07
     všem
    0.07
     ladies
    0.07
     сті
    0.06
    단
    0.06
    ΄
    0.06
    delete
    0.06
     accessing
    0.06
    ření
    0.06
    Act Density 0.006%

    No Known Activations