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

    Neuronpedia

    INDEX
    Explanations

    fast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Що
    -0.07
    ecess
    -0.06
    oted
    -0.06
     علاوه
    -0.06
    loh
    -0.06
    roomId
    -0.06
    ocrine
    -0.06
    Contract
    -0.06
    Якщо
    -0.06
     Conor
    -0.06
    POSITIVE LOGITS
     Sharon
    0.07
    (bodyParser
    0.07
     tutor
    0.06
     tasted
    0.06
     Sampling
    0.06
    ющ
    0.06
     tug
    0.06
    teenth
    0.06
    ,.
    0.06
     petroleum
    0.06
    Act Density 0.001%

    No Known Activations