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

    Neuronpedia

    INDEX
    Explanations

    URLs and Mobile Applications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     charged
    -0.07
    itime
    -0.07
     Machines
    -0.07
    getState
    -0.07
    ่ละ
    -0.06
     Suites
    -0.06
     каз
    -0.06
    (schedule
    -0.06
    요
    -0.06
     ؛
    -0.06
    POSITIVE LOGITS
     overcoming
    0.07
     директор
    0.06
    ampling
    0.06
    uffled
    0.06
    .rate
    0.06
     interesse
    0.06
    _ps
    0.06
     извест
    0.06
    ستم
    0.06
     KBS
    0.06
    Act Density 0.066%

    No Known Activations