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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freshness
    -0.08
    /per
    -0.08
    urkan
    -0.08
     Komple
    -0.08
    -rated
    -0.07
    upal
    -0.07
    一分钟
    -0.07
     sublim
    -0.07
     Schweiz
    -0.07
     washers
    -0.07
    POSITIVE LOGITS
     political
    0.12
    政治
    0.12
     정치
    0.12
     రాజకీయ
    0.11
    军事
    0.11
     military
    0.11
     alliances
    0.11
     राजनीति
    0.11
     politics
    0.11
     militaire
    0.11
    Act Density 0.051%

    No Known Activations