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

    Neuronpedia

    INDEX
    Explanations

    break

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    樹
    -0.07
     Two
    -0.07
     IOS
    -0.07
     udál
    -0.07
    _TOOL
    -0.06
     motors
    -0.06
    шла
    -0.06
     orientations
    -0.06
     Colleges
    -0.06
    加
    -0.06
    POSITIVE LOGITS
     Denied
    0.07
     combineReducers
    0.06
     Certainly
    0.06
     pq
    0.06
     баг
    0.06
     explicitly
    0.06
     pinch
    0.06
     PLEASE
    0.06
    √
    0.06
    illez
    0.06
    Act Density 0.003%

    No Known Activations