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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;↵↵↵
    -0.08
     Stanton
    -0.07
     civilians
    -0.07
    .xrTableCell
    -0.07
    .Graph
    -0.07
    vides
    -0.07
    可通过
    -0.07
     ф
    -0.06
    递给
    -0.06
    сть
    -0.06
    POSITIVE LOGITS
    umni
    0.07
    云
    0.07
    �
    0.07
    ɒ
    0.07
    諸
    0.06
    ENTER
    0.06
    時
    0.06
     Dou
    0.06
    �
    0.06
     enduring
    0.06
    Act Density 0.089%

    No Known Activations