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

    Neuronpedia

    INDEX
    Explanations

    '])

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Blvd
    -0.07
    eceğiz
    -0.06
    Sol
    -0.06
     invokevirtual
    -0.06
    Якщо
    -0.06
     якому
    -0.06
     Boulevard
    -0.06
    Dead
    -0.06
    Author
    -0.06
     pov
    -0.06
    POSITIVE LOGITS
     clic
    0.07
    .expected
    0.06
    /npm
    0.06
    fung
    0.06
    ])-
    0.06
    _Check
    0.06
    ật
    0.06
    "]
↵
    0.06
     TRY
    0.06
    ']==
    0.06
    Act Density 0.001%

    No Known Activations