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

    Neuronpedia

    INDEX
    Explanations

    absolute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    &utm
    -0.07
    (dirname
    -0.07
     hints
    -0.06
    삘
    -0.06
    三种职业
    -0.06
    הזמנה
    -0.06
    LEN
    -0.06
    elize
    -0.06
    学习
    -0.06
    fade
    -0.06
    POSITIVE LOGITS
     naval
    0.08
     toilets
    0.07
    .getProject
    0.07
    Cargo
    0.07
    _Free
    0.07
     annually
    0.07
    果
    0.07
     onPause
    0.07
    GIS
    0.07
     OS
    0.07
    Act Density 0.001%

    No Known Activations