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

    Neuronpedia

    INDEX
    Explanations

    I know what you're thinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tonight
    -0.07
    껨
    -0.07
    㫰
    -0.07
     McM
    -0.07
     Necklace
    -0.07
    倧
    -0.07
     Glas
    -0.06
    -tw
    -0.06
    som
    -0.06
    房车
    -0.06
    POSITIVE LOGITS
     invented
    0.07
    (mean
    0.07
    _retry
    0.07
     compute
    0.07
     mük
    0.07
     vùng
    0.07
     predicates
    0.07
     nymph
    0.07
    销售人员
    0.07
    聯絡
    0.07
    Act Density 0.036%

    No Known Activations