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

    Neuronpedia

    INDEX
    Explanations

    questions and instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scales
    -0.08
     sei
    -0.08
    大姐
    -0.07
     l
    -0.07
    _SCENE
    -0.07
    VAL
    -0.07
    ниц
    -0.07
    科学技术
    -0.07
    Drawer
    -0.07
    нт
    -0.06
    POSITIVE LOGITS
    可以把
    0.07
    優
    0.07
    oundation
    0.07
     Music
    0.06
    泽
    0.06
    :)↵
    0.06
    /weather
    0.06
    yna
    0.06
     '*.
    0.06
    forg
    0.06
    Act Density 0.050%

    No Known Activations