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

    Neuronpedia

    INDEX
    Explanations

    trustworthy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     उल
    -0.07
    l
    -0.06
    -Nazi
    -0.06
    ervention
    -0.06
    偷
    -0.06
    (URL
    -0.06
     recl
    -0.06
    ाजन
    -0.06
    iciones
    -0.06
    acist
    -0.06
    POSITIVE LOGITS
     trustworthy
    0.11
     پای
    0.07
     landscape
    0.07
     advantage
    0.07
    =add
    0.07
     Character
    0.07
     character
    0.06
     –↵
    0.06
    这个
    0.06
    sticks
    0.06
    Act Density 0.009%

    No Known Activations