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

    Neuronpedia

    INDEX
    Explanations

    extracts names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _objects
    -0.07
    ($('.
    -0.07
    能
    -0.06
    éments
    -0.06
     answered
    -0.06
    視
    -0.06
     đáng
    -0.06
     getApp
    -0.06
     百
    -0.06
    imal
    -0.06
    POSITIVE LOGITS
     tady
    0.06
    _base
    0.06
    VERBOSE
    0.06
    лади
    0.06
     #-}↵
    0.06
     SolidColorBrush
    0.06
     dynamically
    0.06
    (LP
    0.06
     racially
    0.05
    итися
    0.05
    Act Density 0.015%

    No Known Activations