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

    Neuronpedia

    INDEX
    Explanations

    flexible, customizable, easy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slums
    0.41
    සේ
    0.37
     haircuts
    0.37
     civilizations
    0.35
     OTHER
    0.35
    定律
    0.35
     pacientes
    0.35
    幔
    0.35
     tribulations
    0.35
    Symptoms
    0.34
    POSITIVE LOGITS
     versatile
    0.80
    เหมาะ
    0.80
     versatility
    0.76
     customizable
    0.74
     easy
    0.71
     flexible
    0.70
    适合
    0.70
     suited
    0.69
    suited
    0.66
     เหมาะ
    0.66
    Act Density 0.036%

    No Known Activations