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

    Neuronpedia

    INDEX
    Explanations

    forum questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sevent
    -0.07
     wherein
    -0.07
    たい
    -0.07
     Groups
    -0.06
    EventManager
    -0.06
    582
    -0.06
     patriarch
    -0.06
    609
    -0.06
     suppressed
    -0.06
     Your
    -0.06
    POSITIVE LOGITS
    ARATION
    0.07
    (DWORD
    0.07
     bás
    0.06
     출
    0.06
    (low
    0.06
    르는
    0.06
    >V
    0.06
     유
    0.06
    ξη
    0.06
     Veranst
    0.06
    Act Density 0.021%

    No Known Activations