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

    Neuronpedia

    INDEX
    Explanations

    explanations and details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =https
    -0.07
     сор
    -0.06
     Sweden
    -0.06
     payday
    -0.06
    헤
    -0.06
    nist
    -0.06
    =wx
    -0.06
     barrel
    -0.06
     buurt
    -0.06
     RESPONS
    -0.06
    POSITIVE LOGITS
    адження
    0.07
    ी-
    0.06
    ‫
    0.06
     علم
    0.06
    genus
    0.06
    .uni
    0.06
    ChildIndex
    0.06
    ●●●●●●●●
    0.06
     orb
    0.06
     Millenn
    0.06
    Act Density 0.099%

    No Known Activations