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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Freedom
    -0.28
     kab
    -0.27
     freedom
    -0.27
    è¿ĽäºĨ
    -0.27
    LC
    -0.25
    ëįĺ
    -0.25
    å·©
    -0.25
    ä¸Ģçľĭ
    -0.24
     isolation
    -0.24
    Freedom
    -0.24
    POSITIVE LOGITS
     fileList
    0.25
     Veget
    0.24
    æľį
    0.24
    pare
    0.24
     Modules
    0.24
    peech
    0.24
     utilization
    0.23
    moduleName
    0.23
    liable
    0.23
    _Util
    0.23
    Act Density 0.011%

    No Known Activations