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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sorts
    -0.46
     للاسماء
    -0.43
    ✨:
    -0.43
     failure
    -0.42
    irability
    -0.40
    delà
    -0.39
    queryInterface
    -0.39
     kteří
    -0.38
    Workbench
    -0.37
     fail
    -0.36
    POSITIVE LOGITS
    principalColumn
    0.67
     nakalista
    0.65
     Linked
    0.64
     Epide
    0.63
     Ca
    0.61
     Citations
    0.60
     Tied
    0.60
     Hurts
    0.58
    قایناق‌لار
    0.57
     Ruins
    0.57
    Act Density 0.000%

    No Known Activations