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

    Neuronpedia

    INDEX
    Explanations

    events, releases, hosting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IFA
    -0.07
    acted
    -0.07
    battle
    -0.06
    外交部
    -0.06
     Caf
    -0.06
     Ath
    -0.06
     tf
    -0.06
     documentos
    -0.06
     Fashion
    -0.06
    Flight
    -0.06
    POSITIVE LOGITS
    훽
    0.07
    ととも
    0.07
    ﹷ
    0.06
     почти
    0.06
    隹
    0.06
    注明出处
    0.06
    缅
    0.06
    每年
    0.06
    东西
    0.06
    '{
    0.06
    Act Density 0.069%

    No Known Activations