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

    Neuronpedia

    INDEX
    Explanations

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뗍
    -0.07
     flew
    -0.07
     falls
    -0.06
    Hol
    -0.06
    .PORT
    -0.06
    inct
    -0.06
    🐊
    -0.06
     fell
    -0.06
     ונ
    -0.06
     Kr
    -0.06
    POSITIVE LOGITS
     pubkey
    0.07
    告诉他
    0.07
     retailer
    0.07
     mockery
    0.07
    urrencies
    0.07
     réalité
    0.07
     regularization
    0.07
    star
    0.07
    亮度
    0.07
    protocol
    0.07
    Act Density 0.029%

    No Known Activations