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

    Neuronpedia

    INDEX
    Explanations

    Agreements/scientific processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.79
     تانيه
    -0.72
    躇
    -0.69
     purpoſe
    -0.69
    MethodManager
    -0.68
     externi
    -0.66
     Paglinawan
    -0.66
     houſe
    -0.65
     tartalomajánló
    -0.63
     Normdatei
    -0.63
    POSITIVE LOGITS
    ,
    0.63
    ↵↵
    0.54
     $
    0.52
     with
    0.50
    setForeground
    0.50
    DataInputStream
    0.48
     far
    0.48
     Rather
    0.48
     some
    0.47
     rather
    0.47
    Act Density 0.127%

    No Known Activations