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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -where"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Package
    -0.06
     Housing
    -0.06
     Wear
    -0.06
    Pause
    -0.06
    )"↵↵
    -0.06
     int
    -0.06
     Execute
    -0.06
    /";↵
    -0.06
     Packages
    -0.06
     documented
    -0.06
    POSITIVE LOGITS
    ımı
    0.07
    605
    0.07
    )))),
    0.07
    /errors
    0.06
    -produced
    0.06
    نج
    0.06
    /entity
    0.06
    �
    0.06
    /actions
    0.06
    θι
    0.06
    Act Density 0.423%

    No Known Activations