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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/code/formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Officers
    -0.07
     experience
    -0.07
    _DOM
    -0.06
     Officer
    -0.06
    088
    -0.06
     officer
    -0.06
     Rounds
    -0.06
     AO
    -0.06
     recordings
    -0.06
     Assassin
    -0.06
    POSITIVE LOGITS
    жив
    0.07
    .
↵
↵
    0.07
     segmentation
    0.06
    .args
    0.06
     pornost
    0.06
    站在
    0.06
    iện
    0.06
    ी।↵
    0.06
     theoretically
    0.06
     viewModel
    0.06
    Act Density 0.000%

    No Known Activations