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

    Neuronpedia

    INDEX
    Explanations

    Brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Actor
    -0.06
    isAdmin
    -0.06
     MSC
    -0.06
    acro
    -0.05
     Pek
    -0.05
     Practices
    -0.05
     Police
    -0.05
     اش
    -0.05
    िस
    -0.05
     FY
    -0.05
    POSITIVE LOGITS
    (sv
    0.07
    Zip
    0.07
    _clear
    0.07
     ((
    0.07
    .KeyCode
    0.07
     newsp
    0.07
     using
    0.07
    (dl
    0.06
     finals
    0.06
     wildfire
    0.06
    Act Density 0.005%

    No Known Activations