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

    Neuronpedia

    INDEX
    Explanations

    presidents leaving/in office

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     envisioned
    -0.07
     STAR
    -0.06
     loos
    -0.06
    ."↵↵↵
    -0.06
    .pdf
    -0.06
    번호
    -0.06
    對
    -0.06
    isContained
    -0.06
    _predicate
    -0.06
    羅
    -0.06
    POSITIVE LOGITS
     labore
    0.07
     jihadist
    0.07
    leave
    0.06
    play
    0.06
    _gui
    0.06
    zM
    0.06
     svo
    0.06
     rapport
    0.06
    取得
    0.06
    Za
    0.06
    Act Density 0.036%

    No Known Activations