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

    Neuronpedia

    INDEX
    Explanations

    beginning of sentences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出入
    -0.09
     thous
    -0.08
     baptized
    -0.07
    ものを
    -0.07
    胧
    -0.07
     o
    -0.07
    テーマ
    -0.07
    諮
    -0.06
    	map
    -0.06
    mqtt
    -0.06
    POSITIVE LOGITS
    []{
    0.07
    Canadian
    0.07
    开场
    0.06
     "["
    0.06
    _Click
    0.06
    _CAPTURE
    0.06
     ARCH
    0.06
    Variant
    0.06
     해결
    0.06
    (DWORD
    0.06
    Act Density 0.001%

    No Known Activations