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

    Neuronpedia

    INDEX
    Explanations

    sentence structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    次
    -0.06
    pdf
    -0.06
    who
    -0.06
     �
    -0.06
     порядке
    -0.06
    _IL
    -0.06
    Statistics
    -0.06
    وجود
    -0.06
    _DIG
    -0.06
     contradictions
    -0.06
    POSITIVE LOGITS
     síd
    0.07
     '%$
    0.06
     toch
    0.06
    沃
    0.06
     zast
    0.06
     Crawford
    0.06
     ngu
    0.06
     середови
    0.06
    ourke
    0.06
    rais
    0.06
    Act Density 0.092%

    No Known Activations