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

    Neuronpedia

    INDEX
    Explanations

    samples/examples

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curt
    -0.07
    /groups
    -0.07
    _choices
    -0.07
    (guess
    -0.07
     |
    -0.07
     Executors
    -0.07
     consort
    -0.07
    辀
    -0.07
    ﯜ
    -0.07
    Presenter
    -0.06
    POSITIVE LOGITS
     amat
    0.07
    だったら
    0.07
    必定
    0.06
     NTN
    0.06
    כן
    0.06
    において
    0.06
    ера
    0.06
     determin
    0.06
    dığımız
    0.06
     때문에
    0.06
    Act Density 0.043%

    No Known Activations