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

    Neuronpedia

    INDEX
    Explanations

    below, under

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     columnIndex
    -0.55
    siąż
    -0.54
     Савезне
    -0.54
    maketitle
    -0.53
    IBAction
    -0.52
    isContained
    -0.52
    Tikang
    -0.52
     NDEBUG
    -0.52
    ekš
    -0.52
    Географија
    -0.51
    POSITIVE LOGITS
     below
    0.64
     under
    0.60
     Below
    0.54
     unter
    0.50
     Tri
    0.50
     onder
    0.49
     Under
    0.49
     to
    0.48
    CodeAttribute
    0.48
    MySql
    0.48
    Act Density 0.001%

    No Known Activations