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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ileaks
    -0.06
    ocha
    -0.06
     Juliet
    -0.06
     đạt
    -0.06
    national
    -0.06
    National
    -0.06
    timestamp
    -0.06
    .pth
    -0.06
     suitability
    -0.06
     Maxwell
    -0.06
    POSITIVE LOGITS
    няття
    0.07
     sở
    0.06
    ่วม
    0.06
    ística
    0.06
     poprvé
    0.06
     Sections
    0.06
    론
    0.06
    =↵
    0.06
     [/
    0.06
    oon
    0.06
    Act Density 0.008%

    No Known Activations