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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tv
    -0.07
    سوب
    -0.06
    Sparse
    -0.06
     Yorkers
    -0.06
    いつ
    -0.06
     CVE
    -0.06
    σφα
    -0.06
    不是
    -0.06
    oolStrip
    -0.06
     саме
    -0.06
    POSITIVE LOGITS
     Authorization
    0.07
     Km
    0.06
    por
    0.06
    "](
    0.06
     Comprehensive
    0.06
     MIC
    0.06
    artment
    0.06
    -Feb
    0.06
     блок
    0.06
     multic
    0.06
    Act Density 0.069%

    No Known Activations