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

    Neuronpedia

    INDEX
    Explanations

    encyclopedia articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ihnen
    -0.08
    .Response
    -0.07
     mir
    -0.07
    循
    -0.07
     thy
    -0.07
     хочу
    -0.07
     python
    -0.06
     usur
    -0.06
    _Device
    -0.06
     сф
    -0.06
    POSITIVE LOGITS
     independent
    0.07
    additional
    0.07
    songs
    0.07
    plets
    0.06
    icional
    0.06
    进货
    0.06
    ORIZ
    0.06
     Während
    0.06
    enic
    0.06
    BALL
    0.06
    Act Density 0.031%

    No Known Activations