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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cılar
    -0.07
     bounded
    -0.07
    中共
    -0.07
    市委常委
    -0.07
     Công
    -0.07
    人大常委
    -0.07
     dừng
    -0.07
    ój
    -0.06
    国の
    -0.06
     monoc
    -0.06
    POSITIVE LOGITS
    rsa
    0.08
    升高
    0.07
     pelic
    0.07
     prompts
    0.07
     disemb
    0.07
    腾飞
    0.07
     printing
    0.07
    哭了
    0.06
    一片
    0.06
     endings
    0.06
    Act Density 0.000%

    No Known Activations