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

    Neuronpedia

    INDEX
    Explanations

    code snippets with hexadecimal values and file permission settings

    oai_token-act-pair · gemini-2.0-flash

    File permissions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.79
    DockStyle
    -0.66
    NameInMap
    -0.64
    Général
    -0.63
    MessageOf
    -0.62
    évaluateur
    -0.61
     ModelExpression
    -0.60
    expandindo
    -0.60
    abestanden
    -0.59
    ///</
    -0.59
    POSITIVE LOGITS
     permissions
    0.60
     mode
    0.58
    mode
    0.57
     modes
    0.53
     owner
    0.52
     permission
    0.52
    permissions
    0.52
     Permissions
    0.52
     perm
    0.51
    link
    0.50
    Act Density 2.364%

    No Known Activations