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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Models
    -0.07
    では
    -0.07
     Territory
    -0.06
    irector
    -0.06
    まま
    -0.06
    venes
    -0.06
     Seas
    -0.06
     Manager
    -0.06
     Accepted
    -0.06
     avoir
    -0.06
    POSITIVE LOGITS
    swagen
    0.06
    Letter
    0.06
    .Groups
    0.06
    SmartyHeaderCode
    0.06
     dubna
    0.06
    \Page
    0.06
    .Minute
    0.06
    .localized
    0.06
    .elapsed
    0.06
    .GraphicsUnit
    0.06
    Act Density 0.042%

    No Known Activations