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

    Neuronpedia

    INDEX
    Explanations

    File extensions and abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _partition
    -0.07
    779
    -0.07
     Geo
    -0.06
     Tokyo
    -0.06
     Tenn
    -0.06
     Otto
    -0.06
    PLAN
    -0.06
     مى
    -0.06
    φέρει
    -0.06
     murdering
    -0.06
    POSITIVE LOGITS
    	cs
    0.07
    š
    0.07
    اقل
    0.07
    expenses
    0.07
     Psi
    0.07
     uns
    0.07
     cs
    0.07
    다운
    0.06
    st
    0.06
    แนะ
    0.06
    Act Density 0.136%

    No Known Activations