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

    Neuronpedia

    INDEX
    Explanations

    Generated text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    択
    -0.08
    -static
    -0.08
    -ten
    -0.07
    /poly
    -0.07
     aantrekk
    -0.07
    (Uri
    -0.07
    .La
    -0.07
    -cont
    -0.07
    -interest
    -0.07
    .ba
    -0.07
    POSITIVE LOGITS
     Foundation
    0.08
    驾
    0.07
     عزیز
    0.07
    ocin
    0.07
     задум
    0.07
     धन्यवाद
    0.07
     thrilled
    0.07
     indispens
    0.07
     gentleman
    0.07
     kan
    0.07
    Act Density 0.121%

    No Known Activations