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

    Neuronpedia

    INDEX
    Explanations

    dates and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Publishing
    -0.06
     tote
    -0.06
    	hit
    -0.06
    atics
    -0.06
     physicians
    -0.06
    .must
    -0.06
    andr
    -0.06
    (firstName
    -0.06
     tax
    -0.06
     Charge
    -0.06
    POSITIVE LOGITS
     뒤
    0.07
     Nissan
    0.07
     uveden
    0.07
     이전
    0.06
     поверхности
    0.06
    NAMESPACE
    0.06
    stup
    0.06
    assistant
    0.06
    ΡΑ
    0.06
    probably
    0.06
    Act Density 0.025%

    No Known Activations