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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Comple
    -0.08
     elek
    -0.07
    sessionId
    -0.07
     Comple
    -0.07
    ｖ
    -0.07
    ��
    -0.07
     cuer
    -0.07
     Expires
    -0.07
     בן
    -0.06
    -v
    -0.06
    POSITIVE LOGITS
    局势
    0.07
    ETA
    0.07
    ellen
    0.06
    사회
    0.06
    EN
    0.06
    open
    0.06
    ods
    0.06
    📃
    0.06
    模板
    0.06
    윷
    0.06
    Act Density 0.009%

    No Known Activations