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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лиц
    -0.07
     ruthless
    -0.07
    arias
    -0.07
     fox
    -0.07
    	action
    -0.07
    package
    -0.07
     noqa
    -0.07
    .minecraftforge
    -0.07
     Lagos
    -0.07
     downloader
    -0.07
    POSITIVE LOGITS
    .AddTransient
    0.08
     Astr
    0.08
    .SetBool
    0.07
    ブラ
    0.06
    윳
    0.06
    과학
    0.06
    ср
    0.06
    及时
    0.06
     toch
    0.06
     szczególn
    0.06
    Act Density 0.010%

    No Known Activations