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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #+#
    -0.71
     HasFactory
    -0.69
    MigrationBuilder
    -0.68
    endphp
    -0.65
    SharedDtor
    -0.63
    SourceChecksum
    -0.60
    lioz
    -0.60
     distanciation
    -0.59
    _));
    -0.58
    vänt
    -0.58
    POSITIVE LOGITS
     ints
    0.68
     type
    0.57
     doubles
    0.52
    doubles
    0.50
     integers
    0.49
    adro
    0.47
    michel
    0.47
    TestTools
    0.46
    ClientSize
    0.45
    agles
    0.45
    Act Density 0.012%

    No Known Activations