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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions, legal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     agreement
    -1.15
    agreement
    -0.94
     agree
    -0.78
    are
    -0.77
     agreements
    -0.66
    agree
    -0.66
     AGREEMENT
    -0.66
     Agreement
    -0.65
    Agreement
    -0.65
    aren
    -0.64
    POSITIVE LOGITS
    EDEFAULT
    0.69
     fallu
    0.65
     contribué
    0.65
    migrationBuilder
    0.65
    caux
    0.65
    SaveChangesAsync
    0.63
     saja
    0.61
     présidentielle
    0.59
     sfondo
    0.59
    inematics
    0.59
    Act Density 0.099%

    No Known Activations