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

    Neuronpedia

    INDEX
    Explanations

    Fighting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Assets
    -0.06
    Japan
    -0.06
    .unsplash
    -0.06
     gehört
    -0.06
    <[
    -0.06
    /vue
    -0.06
     pla
    -0.06
     мол
    -0.06
    ','-
    -0.06
    944
    -0.06
    POSITIVE LOGITS
    siyon
    0.08
    oundation
    0.07
     객
    0.07
    estyle
    0.07
     technical
    0.06
     sustaining
    0.06
    nement
    0.06
    _lin
    0.06
     RCS
    0.06
     tất
    0.06
    Act Density 0.339%

    No Known Activations