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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     *_
    -0.07
    (var
    -0.06
    _hook
    -0.06
    (torch
    -0.06
    不好
    -0.06
    фров
    -0.06
    анд
    -0.06
    .'_
    -0.06
     ري
    -0.06
    osten
    -0.06
    POSITIVE LOGITS
     Buf
    0.08
     üzerinden
    0.07
    detect
    0.06
    xd
    0.06
    olumes
    0.06
     trap
    0.06
     bulunmaktadır
    0.06
    -load
    0.06
     predic
    0.06
     adequ
    0.06
    Act Density 0.191%

    No Known Activations