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

    Neuronpedia

    INDEX
    Explanations

    DNA fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ber
    -0.07
    hx
    -0.07
    Thanks
    -0.07
     Maid
    -0.06
    fx
    -0.06
     sf
    -0.06
    번호
    -0.06
     reactor
    -0.06
    diamond
    -0.06
    _phase
    -0.06
    POSITIVE LOGITS
    現在
    0.07
    ::::
    0.06
     μο
    0.06
    =UTF
    0.06
    reon
    0.06
     NYT
    0.06
    REW
    0.06
    unsqueeze
    0.06
     pneumonia
    0.06
    layıcı
    0.06
    Act Density 0.006%

    No Known Activations