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

    Neuronpedia

    INDEX
    Explanations

    capture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⚆
    -0.08
    _lv
    -0.08
    捶
    -0.08
     święt
    -0.07
    _Timer
    -0.07
     veter
    -0.06
    ↖
    -0.06
     --------------------
    -0.06
     ?↵
    -0.06
     víde
    -0.06
    POSITIVE LOGITS
    czas
    0.08
     killings
    0.07
    Raw
    0.07
    事发
    0.07
    oran
    0.07
    ומי
    0.07
    IRST
    0.07
     bizarre
    0.07
    ImGui
    0.07
    gef
    0.07
    Act Density 0.033%

    No Known Activations