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

    Neuronpedia

    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UserId
    -0.08
    StartDate
    -0.07
     yıldır
    -0.07
     trom
    -0.07
     Successful
    -0.07
    hledem
    -0.07
     weiber
    -0.07
     hats
    -0.07
     checkboxes
    -0.07
    _Height
    -0.07
    POSITIVE LOGITS
     関
    0.06
    ُه
    0.06
    140
    0.06
    .helper
    0.06
    я
    0.06
    ाश
    0.06
     '/',↵
    0.06
    サイト
    0.06
     Autumn
    0.06
    (""
    0.05
    Act Density 0.014%

    No Known Activations