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

    Neuronpedia

    INDEX
    Explanations

    scientific research teams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     免
    -0.07
     버
    -0.07
    kept
    -0.07
    ümü
    -0.06
     良
    -0.06
     retailers
    -0.06
    협
    -0.06
     NumberOf
    -0.06
    .Run
    -0.06
    pathname
    -0.06
    POSITIVE LOGITS
     traumat
    0.06
    INATION
    0.06
     traumatic
    0.06
    :i
    0.06
     Temple
    0.06
    invoices
    0.06
    _PATCH
    0.06
     sb
    0.06
    .Tensor
    0.06
    knowledge
    0.06
    Act Density 0.032%

    No Known Activations