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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     substr
    -0.07
    ческой
    -0.06
    UK
    -0.06
     rand
    -0.06
     ANAL
    -0.06
    .fullName
    -0.06
     Tradable
    -0.06
    ателя
    -0.06
     Dis
    -0.06
     anal
    -0.06
    POSITIVE LOGITS
    mer
    0.07
    asin
    0.06
    983
    0.06
    عمال
    0.06
    dej
    0.06
    夢
    0.06
    std
    0.06
     tipping
    0.06
     tempered
    0.06
    務
    0.06
    Act Density 0.144%

    No Known Activations