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

    Neuronpedia

    INDEX
    Explanations

    user directory paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    平
    0.42
    乌
    0.38
     Antarctica
    0.37
    烏
    0.37
     изменения
    0.37
     objections
    0.36
     rename
    0.36
    мет
    0.35
     Athena
    0.34
     rappel
    0.34
    POSITIVE LOGITS
     hogar
    0.51
    Dir
    0.50
    rootDir
    0.46
    dir
    0.45
     होम
    0.45
    Dirs
    0.44
    Home
    0.43
    ホーム
    0.43
     home
    0.42
    HOME
    0.41
    Act Density 0.001%

    No Known Activations