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

    Neuronpedia

    INDEX
    Explanations

    _template

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Positive
    -0.07
    	swap
    -0.07
     faults
    -0.06
    علوم
    -0.06
     ε
    -0.06
     briefed
    -0.06
    .FETCH
    -0.06
     aio
    -0.06
    _students
    -0.06
    諾
    -0.06
    POSITIVE LOGITS
     BJP
    0.07
     fuck
    0.07
     ‎
    0.06
    _Find
    0.06
     sunscreen
    0.06
    	fire
    0.06
    险
    0.06
     ทำ
    0.06
     Except
    0.06
     использов
    0.06
    Act Density 0.001%

    No Known Activations