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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    karena
    -0.53
     iNdEx
    -0.51
    اران
    -0.51
     Loomis
    -0.49
     margin
    -0.48
     due
    -0.48
    megen
    -0.47
    alka
    -0.47
     giáp
    -0.47
    קל
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.72
    +#+
    0.68
    tvguidetime
    0.65
    󠁢
    0.64
    ReusableCell
    0.63
     تضيفلها
    0.62
    CppMethod
    0.59
    FXML
    0.59
    ConstraintMaker
    0.57
    #+#
    0.56
    Act Density 0.013%

    No Known Activations