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

    Neuronpedia

    INDEX
    Explanations

    temperature increase

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Disp
    -0.07
     sustainable
    -0.07
     Sustainable
    -0.07
     gauge
    -0.07
     bubbles
    -0.07
    _out
    -0.07
    _floor
    -0.06
     정확
    -0.06
     exemple
    -0.06
    _makeConstraints
    -0.06
    POSITIVE LOGITS
    ân
    0.06
    นด
    0.06
    pliant
    0.06
    енти
    0.06
     Wikimedia
    0.06
    .bunifuFlatButton
    0.06
    .test
    0.06
    폴
    0.06
    itical
    0.06
    .EventType
    0.06
    Act Density 0.010%

    No Known Activations