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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lyn
    -0.07
    nameof
    -0.07
    IELDS
    -0.06
     keras
    -0.06
    eslint
    -0.06
     Hod
    -0.06
     انر
    -0.06
    .SetInt
    -0.06
    collections
    -0.06
     nau
    -0.06
    POSITIVE LOGITS
    >'↵
    0.07
     *));↵
    0.07
    %↵↵
    0.07
               ↵
    0.07
    "))
↵
    0.07
    Contours
    0.07
     sentient
    0.07
                   ↵
    0.07
     Official
    0.07
    ..↵↵
    0.06
    Act Density 0.037%

    No Known Activations