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

    Neuronpedia

    INDEX
    Explanations

    code syntax like parentheses, colons, commas, dashes, or double underscores

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.13
    ardless
    -0.64
     initComponents
    -0.59
    ULDER
    -0.58
    //
    -0.52
     UNAM
    -0.52
     Normdatei
    -0.51
    πουργ
    -0.51
    sendRedirect
    -0.50
    ulmuş
    -0.50
    POSITIVE LOGITS
    Composable
    0.59
     Roskov
    0.57
     CreateTagHelper
    0.56
     defaultstate
    0.54
    tvguidetime
    0.53
    ExecuteReader
    0.49
     (°
    0.48
    нциклопе
    0.47
    комму
    0.47
    zé
    0.47
    Act Density 2.462%

    No Known Activations